INDEX

Explanations

mentions of political themes and concepts

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sœur

-0.72

phous

-0.71

 Wray

-0.69

RenderAtEndOf

-0.69

 onBind

-0.68

 Jezus

-0.68

GEBURTS

-0.67

Jumbo

-0.67

wwwwwwww

-0.65

 encan

-0.65

POSITIVE LOGITS

 politics

1.19

 Politics

1.09

 POLITICS

1.06

Politics

1.04

 politic

1.03

politics

0.97

poli

0.94

 politik

0.92

 poli

0.92

 political

0.91

Activations Density 0.064%

mentions of political themes and concepts

No Comments

No Known Activations