INDEX

Explanations

references to espionage and spying activities

oai_token-act-pair · gpt-3.5-turbo

references to espionage and spying activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

xual

-0.93

clus

-0.74

esville

-0.74

à¼

-0.74

opathic

-0.70

ĸļ

-0.69

jiang

-0.67

 Kurd

-0.64

 Centauri

-0.63

ergy

-0.62

POSITIVE LOGITS

glass

0.91

oleon

0.90

ionage

0.82

sonian

0.80

dropping

0.78

 spying

0.76

doms

0.75

OSH

0.75

 spoof

0.71

aroo

0.71

Activations Density 0.030%

references to espionage and spying activities

references to espionage and spying activities

No Comments

No Known Activations