INDEX

Explanations

occurrences of specific punctuation marks

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

after a hyphen

np_acts-logits-general · gemini-2.0-flash

place- or origin-related suffixes

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

-0.78

—

-0.72

–

-0.66

—

-0.61

-0.59

in

-0.56

-0.55

--

-0.53

laughing

-0.50

accharides

-0.50

POSITIVE LOGITS

+#+#

0.96

Efq

0.82

 itſelf

0.80

 raiſ

0.76

 ſtate

0.75

 photolibrary

0.74

 AppColors

0.74

 ་་

0.74

OBO

0.73

 ſche

0.73

Activations Density 0.516%

occurrences of specific punctuation marks

after a hyphen

place- or origin-related suffixes

No Comments

No Known Activations