INDEX

Explanations

quantitative comparisons and numerical data in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

SequentialGroup

-0.49

 IMPLIED

-0.48

Viitteet

-0.44

TabStop

-0.44

SPATH

-0.44

-0.43

OMAS

-0.42

Manbalar

-0.42

EndContext

-0.42

complexType

-0.42

POSITIVE LOGITS

 Италијани

0.72

 uſed

0.68

Eſ

0.68

 Monfieur

0.66

 auffi

0.66

StoreMessageInfo

0.66

liothèque

0.65

 MenuView

0.62

 purpoſe

0.61

Efq

0.59

Activations Density 0.971%

quantitative comparisons and numerical data in the text

No Comments

No Known Activations