INDEX

Explanations

references to third-party involvement or content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 initComponents

-0.58

 ausz

-0.55

 trouvera

-0.54

piecze

-0.51

 hjer

-0.51

Попис

-0.49

reorder

-0.48

клопе

-0.48

 Felt

-0.47

 canina

-0.47

POSITIVE LOGITS

party

0.97

第三方

0.87

 party

0.84

 terceiros

0.81

PARTY

0.80

Party

0.79

 PARTY

0.73

 Party

0.72

τως

0.72

 terceros

0.70

Activations Density 0.190%

references to third-party involvement or content

No Comments

No Known Activations