INDEX

Explanations

mentions of movie-related terms or entities

oai_token-act-pair · gpt-3.5-turbo

references to film ratings and production details

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

ndra

-0.68

anqu

-0.64

jriwal

-0.63

BIP

-0.60

plain

-0.60

 à¤

-0.59

 welfare

-0.58

etooth

-0.58

 Labrador

-0.57

paio

-0.57

POSITIVE LOGITS

 Studios

0.94

 Films

0.94

 Productions

0.88

redits

0.85

 sequels

0.82

 Comics

0.81

 Comic

0.81

 Television

0.79

 Whedon

0.79

 comics

0.78

Activations Density 1.369%

mentions of movie-related terms or entities

references to film ratings and production details

No Comments

No Known Activations