INDEX

Explanations

programming-related terms and functions

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

then, after, expansion

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

esModule

-0.68

 незавершена

-0.65

adaptiveStyles

-0.57

saraba

-0.56

ioutil

-0.54

 nahilalakip

-0.51

RuleContext

-0.50

RTGC

-0.50

 preſent

-0.49

exitRule

-0.49

POSITIVE LOGITS

 undergoing

0.36

ca

0.35

zingen

0.34

 baum

0.34

 undergo

0.34

 spel

0.33

imageFile

0.33

ende

0.33

τ

0.32

 speranza

0.32

Activations Density 0.109%

programming-related terms and functions

then, after, expansion

No Comments

No Known Activations