INDEX

Explanations

instances where the text talks about things being divided or split into categories

oai_token-act-pair · gpt-3.5-turbo

repeated use of the word "divided."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

trak

-0.73

oken

-0.72

ORTS

-0.69

leeve

-0.66

jamin

-0.65

elin

-0.65

ãĥīãĥ©

-0.65

CHA

-0.64

rouse

-0.63

queue

-0.62

POSITIVE LOGITS

 hairs

0.83

iple

0.78

 evenly

0.77

SPL

0.76

rescent

0.74

naire

0.73

 between

0.72

reth

0.71

 unequ

0.71

 alleg

0.71

Activations Density 0.022%

instances where the text talks about things being divided or split into categories

repeated use of the word "divided."

No Comments

No Known Activations