INDEX

Explanations

specific structural or formatting markers in a document, such as placeholders or tags

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

the beginning of new sections or paragraphs in the text

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

comparison and specific topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.20.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

нрави

-0.65

 AssemblyCulture

-0.63

<i>

-0.63

/</

-0.62

.*")]

-0.62

 Schuld

-0.60

chafter

-0.59

видно

-0.59

izhou

-0.58

 تكبرها

-0.58

POSITIVE LOGITS

出版年

0.69

ToFit

0.67

../

0.67

 verwijzen

0.66

 Pyrene

0.65

 Shakspeare

0.63

ated

0.63

 PicClick

0.60

salomon

0.60

 Mehdi

0.59

Activations Density 0.096%

specific structural or formatting markers in a document, such as placeholders or tags

the beginning of new sections or paragraphs in the text

comparison and specific topics

No Comments

No Known Activations