INDEX

Explanations

references to individuals or personal pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ReusableCell

-0.63

unconfirmed

-0.54

ộn

-0.53

 zählt

-0.51

routeProvider

-0.51

hdys

-0.50

sidemargin

-0.48

 InputDecoration

-0.48

Respondent

-0.48

دانشنامهٔ

-0.47

POSITIVE LOGITS

]--;

0.74

 Pter

0.69

ktop

0.66

 onStart

0.60

NUMX

0.59

 $("<

0.58

res

0.57

 onSuccess

0.57

 raiſ

0.56

Dax

0.54

Activations Density 0.022%

references to individuals or personal pronouns

No Comments

No Known Activations