INDEX

Explanations

words related to revisions or changes

oai_token-act-pair · gpt-3.5-turbo

instances of the word "revised" and its variations

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

Negative Logits

OPA

-0.81

bara

-0.81

acht

-0.80

Craft

-0.78

bearing

-0.70

frey

-0.65

culture

-0.63

 Ecology

-0.63

á

-0.62

ech

-0.62

POSITIVE LOGITS

 revisions

0.83

 versions

0.82

 guiActiveUn

0.76

 equilibrium

0.75

 chronological

0.73

 retrospect

0.73

 editions

0.70

 formulations

0.70

 wording

0.70

 revision

0.70

Activations Density 0.018%

words related to revisions or changes

instances of the word "revised" and its variations

No Known Activations