INDEX

Explanations

actions related to authority and conflict

oai_token-act-pair · gpt-3.5-turbo

mentions of violent actions and criminal behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

£ı

-0.83

TPP

-0.66

 curated

-0.65

 spons

-0.65

 endorsements

-0.62

 stoked

-0.60

 leaks

-0.59

 controversies

-0.58

hra

-0.58

 stadiums

-0.58

POSITIVE LOGITS

him

1.39

 them

1.15

 whoever

1.01

him

1.01

Mr

0.98

Ms

0.87

them

0.86

HIM

0.83

 everyone

0.80

Mrs

0.79

Activations Density 0.532%

actions related to authority and conflict

mentions of violent actions and criminal behavior

No Comments

No Known Activations