INDEX

Explanations

markup and code snippets related to configuration files or programming constructs

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

Code snippets; often includes language extensions/formats

np_acts-logits-general · gemini-2.0-flash

code and programming languages

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

 يتيمه

-0.66

AsUp

-0.59

Abit

-0.58

aarrggbb

-0.52

)++;

-0.51

Reentrant

-0.50

jsii

-0.49

 LCCN

-0.48

Vidite

-0.48

createTextNode

-0.47

POSITIVE LOGITS

ReusableCell

0.69

ImageContext

0.59

ագրություններ

0.56

 Pearls

0.55

inon

0.54

SourceChecksum

0.53

出版年

0.51

python

0.51

cell

0.50

findpost

0.50

Activations Density 0.275%

markup and code snippets related to configuration files or programming constructs

Code snippets; often includes language extensions/formats

code and programming languages

No Comments

No Known Activations