INDEX

Explanations

people who are fans of various movies, TV shows, games, or celebrities

oai_token-act-pair · gpt-3.5-turbo

references to fandom or fan communities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ©

-0.61

staff

-0.58

 intervening

-0.57

 flowers

-0.56

urated

-0.55

 unmarked

-0.55

 Pharma

-0.54

 separating

-0.54

 manipulation

-0.53

Prosecut

-0.52

POSITIVE LOGITS

 rejoice

1.18

 beware

0.88

 extraord

0.80

adelphia

0.75

paces

0.75

 alike

0.74

hip

0.73

 aspire

0.72

 cringe

0.72

iuses

0.72

Activations Density 0.123%

people who are fans of various movies, TV shows, games, or celebrities

references to fandom or fan communities

No Comments

No Known Activations