INDEX

Explanations

programming language syntax elements and structure

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

function definitions and code constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 utafitiHapana

-0.53

}?>

-0.48

endcsname

-0.47

InitVars

-0.47

 EconPapers

-0.47



-0.46

felf

-0.46

 desmotivaciones

-0.46

tadr

-0.46

 strconv

-0.45

POSITIVE LOGITS

 HasFactory

0.48

RenderAtEndOf

0.47

invokeLater

0.45

NameInMap

0.45

setObjectName

0.43

MessageTagHelper

0.42

 defaultstate

0.42

.*")]

0.42

SequentialGroup

0.41

NewUrlParser

0.40

Activations Density 0.199%

programming language syntax elements and structure

function definitions and code constructs

No Comments

No Known Activations