INDEX

Explanations

proper nouns related to different individuals

oai_token-act-pair · gpt-3.5-turbo

names of specific individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

PsyNetMessage

-1.09

ORGE

-0.72

ounter

-0.71

 Monetary

-0.65

ocene

-0.61

 stroke

-0.61

 rall

-0.60

helle

-0.60

 Movement

-0.60

POSITIVE LOGITS

 Huff

1.24

ymes

0.98

Sly

0.89

puff

0.86

ness

0.83

meyer

0.81

Gry

0.79

shire

0.79

aday

0.78

beck

0.78

Activations Density 0.011%

proper nouns related to different individuals

names of specific individuals

No Comments

No Known Activations