INDEX

Explanations

code-related logical structures and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

]--;

-0.79

findpost

-0.61

enumi

-0.58

TagMode

-0.58

таратура

-0.54

gemeen

-0.52

fohlen

-0.51

Біографія

-0.49

SFER

-0.49

 ويكيپيديا

-0.47

POSITIVE LOGITS

AppMethodBeat

0.80

 Thank

0.76

Thank

0.72

 thank

0.68

windowFixed

0.68

expandindo

0.62

return

0.61

 useAppContext

0.61

Obrigada

0.59

Danke

0.58

Activations Density 0.086%

code-related logical structures and conditions

No Comments

No Known Activations