INDEX

Explanations

instances of similarity or comparison among different entities or concepts

oai_token-act-pair · gpt-3.5-turbo

phrases that compare objects or concepts with the word "similar."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

erity

-0.83

Limited

-0.73

Added

-0.71

 stoked

-0.69

Published

-0.66

arted

-0.66

azz

-0.66

iott

-0.65

EMENT

-0.63

BF

-0.63

POSITIVE LOGITS

lihood

1.09

 ours

0.97

soDeliveryDate

0.77

 theirs

0.72

lier

0.69

 hers

0.66

inyl

0.62

 those

0.60

oxide

0.60

anism

0.59

Activations Density 0.070%

instances of similarity or comparison among different entities or concepts

phrases that compare objects or concepts with the word "similar."

No Comments

No Known Activations