INDEX

Explanations

examples of movie titles

oai_token-act-pair · gpt-3.5-turbo

variations of semicolons used within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 resil

-0.80

 helicop

-0.77

 unnecess

-0.74

ront

-0.72

ologically

-0.71

stration

-0.70

abee

-0.69

ovy

-0.68

 psychiat

-0.66

agic

-0.66

POSITIVE LOGITS

-)

1.18

âĢ¢âĢ¢âĢ¢âĢ¢

0.88

alias

0.87

 alternatively

0.82

âĢ¢âĢ¢

0.75

cf

0.73

 thence

0.71

 Editing

0.68

IFF

0.66

 Owner

0.64

Activations Density 0.048%

examples of movie titles

variations of semicolons used within a text

No Comments

No Known Activations