INDEX

Explanations

words related to violent actions or situations

oai_token-act-pair · gpt-3.5-turbo

references to violence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ocular

-0.84

erella

-0.78

sonian

-0.78

printed

-0.78

heit

-0.75

STER

-0.73

acent

-0.73

ļéĨĴ

-0.72

artments

-0.71

regon

-0.71

POSITIVE LOGITS

 violence

0.92

 retribution

0.85

 assault

0.85

 deaths

0.83

acre

0.82

 clashes

0.81

 jihad

0.80

 gang

0.80

 suppression

0.79

 scenes

0.79

Activations Density 0.020%

words related to violent actions or situations

references to violence

No Comments

No Known Activations