INDEX

Explanations

phrases indicating lack of knowledge or uncertainty

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "didn't know."

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

ItemTracker

-0.89

ĪĴ

-0.85

isco

-0.83

phrine

-0.75

thren

-0.74

otion

-0.74

ishable

-0.72

uilding

-0.72

attery

-0.72

assi

-0.71

POSITIVE LOGITS

ledge

0.96

how

0.94

lege

0.91

ledged

0.87

 exactly

0.85

 beforehand

0.81

 whether

0.78

 ABOUT

0.76

 enough

0.75

how

0.75

Activations Density 0.042%

phrases indicating lack of knowledge or uncertainty

instances of the phrase "didn't know."

No Comments

No Known Activations