INDEX

Explanations

terms related to measurement or quantification of characteristics

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

]--;

-0.96

cshtml

-0.83

ViewFeatures

-0.78

tvguidetime

-0.75

bcryptjs

-0.73

+#+#

-0.71

/*

-0.71

 insuffisamment

-0.70

 tslint

-0.70

₂+

-0.69

POSITIVE LOGITS

RenderAtEndOf

0.66

bootstrapcdn

0.65

ыгана

0.55

RectangleBorder

0.51

Hentet

0.49

chyma

0.49

verwijspagina

0.47

 فريبيس

0.46

ьажоргаш

0.44

">)</

0.42

Activations Density 1.668%

terms related to measurement or quantification of characteristics

No Comments

No Known Activations