INDEX

Explanations

phrases indicative of policy-making or governmental actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ScopeManager

-0.91

ContentAsync

-0.82

uxxxx

-0.82

 виправивши

-0.78

 kaynağından

-0.76

DeleteBehavior

-0.71

migrationBuilder

-0.70

rungsseite

-0.69

 nahilalakip

-0.66

ValueStyle

-0.63

POSITIVE LOGITS

__':

0.52

__':

0.48

zuk

0.47

"])){

0.43

kheim

0.43

 magically

0.41

DECREF

0.41

]]>

0.41

outine

0.41

}))

0.41

Activations Density 0.516%

phrases indicative of policy-making or governmental actions

No Comments

No Known Activations