INDEX

Explanations

commands or instructions that involve action

oai_token-act-pair · gpt-3.5-turbo

actions or commands directed at the reader

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

HCR

-0.79

DragonMagazine

-0.63

ARP

-0.63

 await

-0.63

 Various

-0.60

among

-0.59

Applic

-0.59

Vs

-0.59

minecraft

-0.59

enic

-0.58

POSITIVE LOGITS

 yourself

0.73

 somebody

0.70

 google

0.68

 blindly

0.66

 correctly

0.66

 incorrectly

0.65

 disrespect

0.65

 lucky

0.62

appropriate

0.60

 THESE

0.59

Activations Density 0.199%

commands or instructions that involve action

actions or commands directed at the reader

No Comments

No Known Activations