INDEX

Explanations

non-word separators and punctuation marks

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

Punctuations like comma, semicolon, brackets

np_acts-logits-general · gemini-2.0-flash

list delimiters and punctuation

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

enumi

-0.85

GraphicsUnit

-0.68

fromnode

-0.66

 كومونز

-0.66

 Профиль

-0.65

AnchorStyles

-0.64

 typelib

-0.63

GetAxis

-0.60

 désolés

-0.60

存于互联网档案馆

-0.59

POSITIVE LOGITS

etc

0.90

","","

0.74

','',

0.68

etc

0.68

}(),

0.65

,\

0.64

","\

0.62

0.61

[],

0.61

/=

0.61

Activations Density 0.317%

non-word separators and punctuation marks

Punctuations like comma, semicolon, brackets

list delimiters and punctuation

No Comments

No Known Activations