INDEX

Explanations

specialized formatting or annotation markers in the text

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

Preceding punctuation or symbols

np_acts-logits-general · gemini-2.0-flash

mathematical and technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

!...

-0.54

...!

-0.53

!$

-0.51

UnknownFieldSet

-0.51

!..

-0.49

Diwedd

-0.48

!$

-0.48

izoen

-0.48

......

-0.47

........

-0.47

POSITIVE LOGITS

 Date

0.69

oa̍t

0.65

harapkan

0.63

Buy

0.62

OGND

0.61

CodedInputStream

0.59

حياتها

0.56

tagHelperRunner

0.54

)':

0.53

webElementXpaths

0.53

Activations Density 0.039%

specialized formatting or annotation markers in the text

Preceding punctuation or symbols

mathematical and technical contexts

No Comments

No Known Activations