INDEX

Explanations

terms related to national identity and legal status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

expandindo

-0.72

uesia

-0.68

WebElementEntity

-0.60

 Mathi

-0.59

 незавершена

-0.59

Iden

-0.58

出版年

-0.58

 Pauli

-0.57

WarningLevel

-0.54

 ehrlich

-0.54

POSITIVE LOGITS

ants

1.05

ant

1.02

ANT

0.89

rant

0.79

ante

0.79

anto

0.75

ANTE

0.74

anten

0.74

ANTS

0.72

Ant

0.71

Activations Density 2.577%

terms related to national identity and legal status

No Comments

No Known Activations