INDEX

Explanations

code-related elements, such as file includes and class definitions

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

programming library includes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 ExecuteAsync

-0.55

 Taktlose

-0.52

webElementXpaths

-0.52

RepeatedField

-0.48

 pleaſure

-0.47

FunctionFlags

-0.46

rawDesc

-0.46

 nakalista

-0.44

UserScript

-0.44

 ModelExpression

-0.43

POSITIVE LOGITS

ⓘ

0.58

Per

0.54

0.53

 Search

0.51

 Over

0.50

De

0.50

Un

0.50

Au

0.49

 Class

0.49

Activations Density 0.004%

code-related elements, such as file includes and class definitions

programming library includes

No Comments

No Known Activations