INDEX

Explanations

references to significant events or news related to individuals or society

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

preceding time or location

np_acts-logits-general · gemini-2.0-flash

news yesterday

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

wußt

-0.48

 inoltre

-0.48

lardır

-0.48

 rağmen

-0.46

"]];

-0.46

"]=

-0.45

sequently

-0.43

 επίσης

-0.43

 также

-0.42

ləş

-0.42

POSITIVE LOGITS

 courtesy

0.98

courtesy

0.89

 thanks

0.83

 cortesía

0.82

 disambiguazione

0.82

 yonder

0.79

ViewFeatures

0.79

ain

0.78

 graças

0.78

 CreateTagHelper

0.77

Activations Density 0.568%

references to significant events or news related to individuals or society

preceding time or location

news yesterday

No Comments

No Known Activations