INDEX

Explanations

programming language syntax and structure

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

`#include` directives 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 @ 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

argb

-0.49

brainly

-0.48

saurus

-0.47

WEBPACK

-0.47

 ControllerBase

-0.46

 Exactos

-0.46

JdbcTemplate

-0.45

 erop

-0.44

 Administrativna

-0.44

vez

-0.44

POSITIVE LOGITS

 propOrder

0.49

 defaultstate

0.49

EndProject

0.45

 ujednoznacz

0.44

 autorytatywna

0.43

sidemargin

0.43

 myſelf

0.42

 AssemblyCulture

0.40

 surla

0.40

 '\\;'

0.40

Activations Density 0.000%

programming language syntax and structure

`#include` directives or `user` input

No Comments

No Known Activations