INDEX

Explanations

specific identifiers or codes related to data or files

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

jsfiddle links

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 voluntarily

-0.37

geli

-0.36

ั

-0.36

énéral

-0.35

 Vanity

-0.35

 absolutely

-0.34

Tev

-0.34

 clichés

-0.34

mologie

-0.34

ひ

-0.34

POSITIVE LOGITS

 propOrder

0.59

 виправивши

0.57

 ProtoMessage

0.56

exitRule

0.54

 AssemblyCulture

0.49

 '\\;'

0.49

ंदीखरीदारी

0.49

AddTagHelper

0.48

хьтан

0.47

vierno

0.47

Activations Density 0.002%

specific identifiers or codes related to data or files

jsfiddle links

No Comments

No Known Activations