INDEX

Explanations

programming-related syntax and definitions

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

action, delete, try, exam

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

transQ

-0.76

AISSEE

-0.73

 المعيارى

-0.63

WebElementEntity

-0.60

 betweenstory

-0.58

astéroïdes

-0.57

 '\\;'

-0.57

httphttps

-0.56

 pinulongan

-0.56

 Geſch

-0.55

POSITIVE LOGITS

MessageOf

0.36

CompilerServices

0.36

 parts

0.34

IntoConstraints

0.33

 cheeses

0.33

colgroup

0.33

それに

0.32

ConstraintMaker

0.32

 nothin

0.31

sidemargin

0.31

Activations Density 0.029%

programming-related syntax and definitions

action, delete, try, exam

No Comments

No Known Activations