INDEX

Explanations

names of individuals and their affiliations

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

names in lists

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

 poveznice

-0.63

WriteTagHelper

-0.59

 ddelweddau

-0.58

LookAnd

-0.57

-------------</

-0.56

 surla

-0.54

ⓧ

-0.54

 esigen

-0.54

 незавершена

-0.54

IsContent

-0.51

POSITIVE LOGITS

ArgsConstructor

0.38

CrossRef

0.36

ensement

0.33

 contributed

0.29

printStackTrace

0.28

 juges

0.28

,‎

0.27

 warrant

0.27

Activités

0.27

 sonore

0.27

Activations Density 0.012%

names of individuals and their affiliations

names in lists

No Comments

No Known Activations