INDEX

Explanations

details about people and their actions

oai_token-act-pair · gpt-3.5-turbo

references to victims and their backgrounds

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

eur

-0.57

 regulation

-0.57

prem

-0.57

ifice

-0.56

 banning

-0.55

Insert

-0.55

 Limit

-0.54

 Built

-0.54

forcement

-0.54

 PRESS

-0.54

POSITIVE LOGITS

selves

0.96

 disembark

0.94

 individually

0.89

 congreg

0.89

 evacuated

0.85

 numbered

0.84

 surn

0.81

 themselves

0.80

 dispersed

0.79

 volunte

0.79

Activations Density 0.718%

details about people and their actions

references to victims and their backgrounds

No Comments

No Known Activations