INDEX

Explanations

references to violent actions and the implications of such actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nonatomic

-0.57

 հղումներ

-0.57

солю

-0.53

DockStyle

-0.51

 Capital

-0.49

KommentareTeilen

-0.47

valores

-0.47

EDEFAULT

-0.46

Pipe

-0.45

pip

-0.44

POSITIVE LOGITS

ंदीखरीदारी

0.61

 FBref

0.56

 بيها

0.56

\}\\

0.54

();)

0.52

theless

0.52

 informée

0.52

HideFlags

0.51

sbericht

0.51

Хороший

0.51

Activations Density 0.237%

references to violent actions and the implications of such actions

No Comments

No Known Activations