INDEX

Explanations

mentions of specific names or terms with "Hed" in them

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

EED

-0.73

Leary

-0.71

auts

-0.71

eers

-0.68

AU

-0.68

tenance

-0.68

xon

-0.68

chnology

-0.67

 Mellon

-0.65

aic

-0.65

POSITIVE LOGITS

nesday

1.06

rid

0.94

gp

0.89

ged

0.85

iqueness

0.84

glers

0.83

gew

0.81

rick

0.80

stract

0.78

riks

0.78

Activations Density 0.018%

mentions of specific names or terms with "Hed" in them

proper nouns, particularly names of people and places

No Comments

No Known Activations