INDEX

Explanations

words related to destructive acts such as vandalism, arson, and graffiti

oai_token-act-pair · gpt-3.5-turbo

instances of vandalism and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

croft

-0.85

vana

-0.80

abol

-0.77

ramid

-0.77

pres

-0.75

obar

-0.75

equal

-0.73

gravity

-0.71

erald

-0.71

omo

-0.70

POSITIVE LOGITS

 vandalism

1.29

 vandal

1.09

 graffiti

1.06

 spree

0.99

 leve

0.82

 dere

0.81

 arson

0.76

 scaven

0.75

 rampage

0.74

ruction

0.70

Activations Density 0.013%

words related to destructive acts such as vandalism, arson, and graffiti

instances of vandalism and related terms

No Comments

No Known Activations