INDEX

Explanations

phrases related to presenting or proposing something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating proposals or arguments being presented

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Chaser

-0.61

 Copyright

-0.58

illary

-0.58

ģ«

-0.57

 Moonlight

-0.56

 drinkers

-0.56

 Indones

-0.55

Expl

-0.55

COLOR

-0.54

 hatch

-0.54

POSITIVE LOGITS

sole

0.84

rir

0.75

utical

0.74

iris

0.73

lehem

0.70

tu

0.69

*/(

0.69

igs

0.69

aval

0.69

ulhu

0.68

Activations Density 0.067%

phrases related to presenting or proposing something

phrases indicating proposals or arguments being presented

No Known Activations