INDEX

Explanations

references to geographical locations

oai_token-act-pair · gpt-3.5-turbo

names of people and their relationships

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

incial

-0.51

 discretion

-0.51

 judgement

-0.50

 censor

-0.50

".[

-0.50

 cens

-0.49

 endeavour

-0.49

 infall

-0.48

 downwards

-0.48

 incompetence

-0.48

POSITIVE LOGITS

 leukemia

0.58

obar

0.56

 photographed

0.52

 Shutterstock

0.52

Picture

0.46

 Mour

0.46

umbnails

0.46

 Lenn

0.45

overed

0.45

utterstock

0.44

Activations Density 1.735%

references to geographical locations

names of people and their relationships

No Comments

No Known Activations