INDEX

Explanations

legal and governmental terms related to authority and judgment

oai_token-act-pair · gpt-4o-mini Triggered by @bot

the neuron spots salient content words, especially proper nouns and other named/technical terms (e.g., names, institutions, and domain-specific nouns).

oai_token-act-pair · gpt-5-mini Triggered by @phamvanluong2003

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kysy

-0.62

 виправивши

-0.61

 springfox

-0.56

 CURIAM

-0.54

CodedInputStream

-0.48

CreateInfo

-0.48

parsedMessage

-0.47

 EconPapers

-0.47

 soft

-0.47

dera

-0.47

POSITIVE LOGITS

onAttach

0.60

LookAnd

0.56

 bologna

0.55

ego

0.54

 الاطلاع

0.52

клопе

0.52

ChildIndex

0.50

 fals

0.49

 OnInit

0.49

styleUrls

0.49

Activations Density 0.858%

legal and governmental terms related to authority and judgment

the neuron spots salient content words, especially proper nouns and other named/technical terms (e.g., names, institutions, and domain-specific nouns).

No Comments

No Known Activations