INDEX

Explanations

programming-related syntax and delimiters

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

C preprocessor directives

np_acts-logits-general · gemini-2.0-flash

code definitions and system calls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

idste

-0.47

 close

-0.46

 promosi

-0.46

 bouche

-0.44

chard

-0.43

caccio

-0.43

linearGradient

-0.43

-0.41

 būs

-0.41

 suami

-0.41

POSITIVE LOGITS

\{\\

0.85

rrggbb

0.84

 '\\;'

0.83

setVerticalGroup

0.82

 للاسماء

0.81

دانشنامهٔ

0.75

})]

0.72

verwijspagina

0.72

ThroughAttribute

0.71

 للمعارف

0.71

Activations Density 1.135%

programming-related syntax and delimiters

C preprocessor directives

code definitions and system calls

No Comments

No Known Activations