INDEX

Explanations

corrections or clarifications in articles

oai_token-act-pair · gpt-3.5-turbo

references to specific articles or versions of content

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çĶ°

-0.80

apes

-0.75

gans

-0.74

okers

-0.73

APD

-0.72

aws

-0.72

ickets

-0.71

loads

-0.70

trump

-0.69

marks

-0.69

POSITIVE LOGITS

 particular

1.05

 article

0.84

 millennium

0.79

 century

0.78

 newfound

0.77

 alleged

0.76

 latter

0.76

 purported

0.76

 week

0.75

 month

0.75

Activations Density 0.087%

corrections or clarifications in articles

references to specific articles or versions of content

No Comments

No Known Activations