INDEX

Explanations

return statements 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 @ 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

WillAppear

-0.72

 resourceCulture

-0.71

"]();

-0.60

">)</

-0.58

'}),

-0.55

>",

-0.54

parsedMessage

-0.54

__':

-0.53

__':

-0.52

 Salta

-0.51

POSITIVE LOGITS

 تانيه

0.91

saraba

0.74

الدراسه

0.72

NewUrlParser

0.70

țin

0.69

govina

0.68

aragua

0.68

argout

0.67

ʐ

0.67

ectoria

0.66

Activations Density 0.041%

return statements in code

No Comments

No Known Activations