INDEX

Explanations

references to violent acts and criminal incidents

oai_token-act-pair · gpt-3.5-turbo

phrases related to crime and violence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

(#

-0.63

Factor

-0.62

ist

-0.61

 Minion

-0.60

osaurus

-0.60

dict

-0.59

ouble

-0.58

iel

-0.57

otally

-0.55

toc

-0.55

POSITIVE LOGITS

agher

0.92

eating

0.69

rawdownloadcloneembedreportprint

0.67

swick

0.66

opian

0.66

Britain

0.64

accompan

0.64

mercial

0.62

England

0.61

 Blackburn

0.61

Activations Density 0.128%

references to violent acts and criminal incidents

phrases related to crime and violence

No Comments

No Known Activations