INDEX

Explanations

the beginning of various text segments or sections in a document

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

lists with numbers

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 CreateTagHelper

-1.17

 ModelExpression

-1.13

ScopeManager

-1.05

 consultato

-0.96

AccessorTable

-0.89

تقاوى

-0.81

 وتسجيلات

-0.80

parsedMessage

-0.79

ImageContext

-0.79

migrationBuilder

-0.78

POSITIVE LOGITS

<eos>

0.98

↵↵

0.85

↵↵↵

0.75

</blockquote>

0.74

↵↵↵↵

0.59

↵

0.58

</h3>

0.56

 quoted

0.56

</h5>

0.54

*/

0.54

Activations Density 0.049%

the beginning of various text segments or sections in a document

lists with numbers

No Comments

No Known Activations