INDEX

Explanations

people's names or words related to places and medical conditions

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 cellul

-0.71

é¾įå¥ĳå£«

-0.69

»Ĵ

-0.68

 bluff

-0.66

lication

-0.62

ãģ¦

-0.60

 condem

-0.60

 stewards

-0.59

dayName

-0.59

ãĥ¯ãĥ³

-0.59

POSITIVE LOGITS

ocene

0.81

orce

0.76

andro

0.72

ocyte

0.72

 Observatory

0.70

isite

0.70

voy

0.69

velt

0.69

owship

0.68

doms

0.68

Activations Density 0.090%

people's names or words related to places and medical conditions

proper nouns, specifically names of people and organizations

No Comments

No Known Activations