INDEX

Explanations

references to individuals and their contributions in academic discussions

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

pronouns and names followed by actions/roles

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

 utafitiHapana

-0.41

 wireType

-0.39

Diweddarwch

-0.39

ſtanding

-0.37

ighborhood

-0.36

 gynhyrchwyd

-0.36

expandindo

-0.35

今日の

-0.35

 électriques

-0.35

iNdEx

-0.34

POSITIVE LOGITS

 ModelExpression

0.64

 createState

0.60

 himself

0.46

ArgumentParser

0.46

 GoogleFonts

0.45

marshal

0.44

帖最后由

0.43

 suggested

0.43

ceğini

0.43

AnchorTagHelper

0.42

Activations Density 0.084%

references to individuals and their contributions in academic discussions

pronouns and names followed by actions/roles

No Comments

No Known Activations