INDEX

Explanations

words related to measurements or values on a scale

oai_token-act-pair · gpt-3.5-turbo

words related to concentration or density

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

acca

-0.86

channelAvailability

-0.85

gb

-0.78

HCR

-0.76

soDeliveryDate

-0.75

éĹĺ

-0.75

isSpecialOrderable

-0.74

HEAD

-0.71

qv

-0.71

NK

-0.70

POSITIVE LOGITS

enary

1.06

imeter

0.99

ennial

0.98

rate

0.97

een

0.95

rity

0.95

rates

0.94

rations

0.92

ration

0.89

imet

0.88

Activations Density 0.007%

words related to measurements or values on a scale

words related to concentration or density

No Comments

No Known Activations