INDEX

Explanations

victims of various situations or issues

oai_token-act-pair · gpt-3.5-turbo

references to victims of various crimes and injustices

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

oday

-0.82

MX

-0.76

yip

-0.74

soDeliveryDate

-0.74

ulum

-0.74

readable

-0.70

ortment

-0.69

ary

-0.69

heit

-0.68

rier

-0.68

POSITIVE LOGITS

 ingest

0.80

gou

0.71

 metic

0.69

 psych

0.68

 suff

0.66

 untreated

0.66

 displacement

0.64

 starvation

0.63

Ö¼

0.63

 either

0.63

Activations Density 0.083%

victims of various situations or issues

references to victims of various crimes and injustices

No Comments

No Known Activations