INDEX

Explanations

references to photographic credits or sources in articles

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

AndEndTag

-0.61

yarnpkg

-0.56

npmjs

-0.53

 DBNull

-0.48

IsInitialized

-0.48

 nakalista

-0.47

 certain

-0.46

 Réponses

-0.45

ষ্

-0.45

โน

-0.44

POSITIVE LOGITS

 Courtesy

0.85

courtesy

0.81

Courtesy

0.79

tyimages

0.78

UTERS

0.74

 courtesy

0.74

Getty

0.73

 Shutterstock

0.72

(@"%@",

0.71

Hochspringen

0.70

Activations Density 0.129%

references to photographic credits or sources in articles

No Comments

No Known Activations