INDEX

Explanations

references to Australian culture

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

Unusual words or names

np_acts-logits-general · gemini-2.0-flash

specific list items

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DoubleQuotes

-0.70

 للاسماء

-0.59

 الحره

-0.59

 renseignements

-0.58

 fubject

-0.56

jgl

-0.54

 fevere

-0.53

ungsbedingungen

-0.53

 very

-0.52

Very

-0.52

POSITIVE LOGITS

нибудь

0.68

 plastique

0.58

 irgend

0.56

 irgende

0.56

 fucking

0.55

 helst

0.51

 очеред

0.50

 sotto

0.50

zęd

0.50

NameInMap

0.48

Activations Density 0.338%

references to Australian culture

Unusual words or names

specific list items

No Comments

No Known Activations