INDEX

Explanations

phrases indicating clarity or explicitly making statements

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "made it clear."

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

umbn

-0.75

isol

-0.75

asus

-0.71

utsu

-0.69

 crane

-0.65

exper

-0.64

 Derby

-0.64

otin

-0.63

oleon

-0.62

igor

-0.62

POSITIVE LOGITS

ances

0.90

 distinctions

0.79

 distinction

0.78

ance

0.76

 upfront

0.75

gow

0.73

 explicitly

0.71

\\\\\\\\

0.69

ered

0.69

forth

0.69

Activations Density 0.028%

phrases indicating clarity or explicitly making statements

instances of the phrase "made it clear."

No Comments

No Known Activations