INDEX

Explanations

the abbreviation "DR" or words beginning with "dr" in the text

oai_token-act-pair · gpt-3.5-turbo

references to the term "DR" in various contexts

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

 Corpus

-0.91

eers

-0.88

ERN

-0.85

eering

-0.74

eer

-0.73

 Pose

-0.71

quo

-0.69

yip

-0.68

Nun

-0.65

SHIP

-0.62

POSITIVE LOGITS

agons

1.20

inking

1.13

unks

1.02

unk

1.02

adeon

0.99

inks

0.98

inker

0.97

aining

0.97

udge

0.95

iller

0.94

Activations Density 0.034%

the abbreviation "DR" or words beginning with "dr" in the text

references to the term "DR" in various contexts

No Comments

No Known Activations