INDEX

Explanations

words related to explosions, disruptions, or intense actions

oai_token-act-pair · gpt-3.5-turbo

words related to burial and death

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

idious

-0.80

 Citation

-0.59

forward

-0.58

 intervening

-0.57

 Benedict

-0.56

 Rooney

-0.55

CoC

-0.55

 Mara

-0.53

 Wilkinson

-0.53

orno

-0.52

POSITIVE LOGITS

ger

1.04

cers

1.04

ged

0.96

ges

0.93

sts

0.92

cer

0.87

ts

0.86

ctions

0.84

gers

0.84

geon

0.83

Activations Density 0.100%

words related to explosions, disruptions, or intense actions

words related to burial and death

No Comments

No Known Activations