INDEX

Explanations

function and method definitions in code

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

-0.66

ImageContext

-0.52

'||

-0.51

ContainsKey

-0.51

wußt

-0.51

gru

-0.50

 Escu

-0.50

ste

-0.50

 Centr

-0.49

>";

-0.49

POSITIVE LOGITS

 return

0.89

 returns

0.86

return

0.85

Returns

0.84

returns

0.79

 ritorno

0.77

 RETURNS

0.71

 Returns

0.71

 retour

0.69

 retourner

0.67

Activations Density 0.056%

function and method definitions in code

No Comments

No Known Activations