INDEX

Explanations

mentions of various forms of torture

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept and practice of torture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

soType

-0.84

nect

-0.66

Merit

-0.64

 Financial

-0.64

ership

-0.63

abeth

-0.63

agall

-0.63

 Forbes

-0.62

interstitial

-0.62

 lender

-0.60

POSITIVE LOGITS

 torture

0.92

APE

0.80

 chambers

0.79

imony

0.75

rs

0.75

 interrogation

0.74

 tactics

0.74

 interrog

0.73

 captives

0.73

apons

0.72

Activations Density 0.040%

mentions of various forms of torture

terms related to the concept and practice of torture

No Comments

No Known Activations