INDEX

Explanations

punctuation marks or symbols, especially those often associated with formatting

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

Punctuation before specific words

np_acts-logits-general · gemini-2.0-flash

case:

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

 myſelf

-0.96

 كومونز

-0.96

PWN

-0.91

 laun

-0.89

Efq

-0.87

)+"

-0.83

 ſeveral

-0.83

 Majefty

-0.81

 ſame

-0.80

 Jamestown

-0.80

POSITIVE LOGITS

いる

1.00

iwa

0.84

 Humphries

0.83

sertation

0.81

出版年

0.80

 Rosenthal

0.80

 Ayres

0.75

sons

0.73

eniu

0.73

0.71

Activations Density 0.253%

punctuation marks or symbols, especially those often associated with formatting

Punctuation before specific words

case:

No Comments

No Known Activations