INDEX

Explanations

phrases describing roles and influences related to gender in various contexts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Zij

-0.48

 válido

-0.47

localctx

-0.46

migrationBuilder

-0.45

봤

-0.45

erio

-0.44

//

-0.44

раздо

-0.44

Applies

-0.44

 fallback

-0.44

POSITIVE LOGITS

Personendaten

0.77

 Signalez

0.75

InvalidProtocol

0.68

 оригіналу

0.63

 &___

0.60

 للاسماء

0.59

 ligiloj

0.59

HasForeignKey

0.59

PMailer

0.59

GraphicsUnit

0.59

Activations Density 0.490%

phrases describing roles and influences related to gender in various contexts

No Comments

No Known Activations