INDEX

Explanations

instances of the word "list" and its usage in code contexts

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

list manipulation or user input

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

 Roskov

-0.46

stateProvider

-0.40

 beginnetje

-0.40

ParallelGroup

-0.38

AutoScaleMode

-0.37

">*</

-0.36

PreInfinity

-0.36

glTexCoord

-0.36

 QtCore

-0.35

imwrite

-0.35

POSITIVE LOGITS

########.

0.51

NameInMap

0.48

MigrationBuilder

0.45

yonel

0.45

newArrayList

0.44

ised

0.42

يكب

0.42

tisseur

0.42

sprozess

0.41

 Italijanski

0.41

Activations Density 0.003%

instances of the word "list" and its usage in code contexts

list manipulation or user input

No Comments

No Known Activations