INDEX

Explanations

phrases that indicate comparison or contrast between different entities

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

Negative Logits

Hic

-0.66

 relationship

-0.66

 relations

-0.65

 connection

-0.65

 fixer

-0.65

titleMargin

-0.64

MENAFN

-0.62

 relationships

-0.61

Portály

-0.59

 connections

-0.58

POSITIVE LOGITS

ěstí

0.63

StructEnd

0.61

AsUp

0.60

ïsme

0.58

complexType

0.57

 fumée

0.56

ыгана

0.55

tivitas

0.54

 juges

0.54

وصف

0.53

Activations Density 0.038%

phrases that indicate comparison or contrast between different entities

No Known Activations