INDEX

Explanations

phrases related to continuation, quick actions, and important steps or measures

oai_token-act-pair · gpt-3.5-turbo

phrases indicating summaries or descriptions of various topics

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

seys

-0.89

alties

-0.84

ween

-0.83

ngth

-0.79

oes

-0.78

dies

-0.78

aneers

-0.75

obiles

-0.72

bats

-0.70

lime

-0.69

POSITIVE LOGITS

 conjecture

0.71

 blatant

0.70

 bold

0.68

 continuation

0.68

 unintentional

0.68

 prol

0.68

ado

0.66

 moot

0.66

DAR

0.65

PvP

0.65

Activations Density 0.269%

phrases related to continuation, quick actions, and important steps or measures

phrases indicating summaries or descriptions of various topics

No Known Activations