INDEX

Explanations

phrases or structures that indicate conditions or stipulations in arguments

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

after commas in opinionated text

np_acts-logits-general · gemini-2.0-flash

commas followed by common words

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

)});

-0.53

ControllerAdvice

-0.46

dao

-0.44

丘

-0.44

 \%}$

-0.43

 Rood

-0.43

/*!

-0.43

 입니다

-0.42

}));

-0.42

 nanti

-0.42

POSITIVE LOGITS

 nevertheless

1.22

 nonetheless

1.09

 dennoch

0.93

それでも

0.92

 Dennoch

0.91

 Nonetheless

0.91

 Nevertheless

0.89

 unknownFields

0.89

Nonetheless

0.89

Nevertheless

0.87

Activations Density 0.189%

phrases or structures that indicate conditions or stipulations in arguments

after commas in opinionated text

commas followed by common words

No Comments

No Known Activations