INDEX

Explanations

mentions of policy-related terms and discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

__':

-0.65

aneous

-0.60

 تضيفلها

-0.60

 cherchés

-0.58

gister

-0.56

تقاوى

-0.55

🏻

-0.54

TintMode

-0.54

żd

-0.54

BarStyle

-0.53

POSITIVE LOGITS

 policies

0.90

maker

0.89

Policies

0.85

making

0.80

 makers

0.79

 Policies

0.78

makers

0.71

policies

0.69

holder

0.68

holders

0.65

Activations Density 0.052%

mentions of policy-related terms and discussions

No Comments

No Known Activations