INDEX

Explanations

Words related to notable people or places

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 optionally

-0.61

 undo

-0.60

 assail

-0.58

 brakes

-0.57

 scalp

-0.56

 Ahead

-0.55

 enlight

-0.55

 haircut

-0.55

elight

-0.55

 NIGHT

-0.55

POSITIVE LOGITS

acan

0.95

æ©

0.82

é¾įå

0.78

umerable

0.74

archs

0.71

olit

0.70

orio

0.70

raq

0.69

zag

0.68

throp

0.68

Activations Density 0.106%

Words related to notable people or places

proper nouns and names

No Comments

No Known Activations