INDEX

Explanations

single characters

oai_token-act-pair · gpt-3.5-turbo

unique characters or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ufact

-1.09

merce

-0.90

 ethic

-0.83

psey

-0.83

 carbohyd

-0.82

raviolet

-0.81

 synerg

-0.80

 volunte

-0.79

wcs

-0.78

secut

-0.76

POSITIVE LOGITS

Ī

1.18

Ĩ

1.18

ĩ

1.04

ÃįÃį

1.03

ãĤĭ

0.97

Ĺ

0.96

ãĥĺ

0.96

ÙĦ

0.94

Ðµ

0.93

İ

0.93

Activations Density 0.003%

single characters

unique characters or symbols

No Comments

No Known Activations