INDEX

Explanations

percentages mentioned within text

oai_token-act-pair · gpt-3.5-turbo

phrases indicating percentages

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

kefeller

-0.80

Attributes

-0.77

GROUP

-0.74

Rav

-0.72

ALLY

-0.70

IDES

-0.69

PORT

-0.68

FIN

-0.66

ITED

-0.66

Family

-0.66

POSITIVE LOGITS

imet

1.30

imeter

1.05

rate

0.82

rations

0.77

enary

0.74

urion

0.74

uary

0.74

rated

0.74

oning

0.73

bench

0.70

Activations Density 0.032%

percentages mentioned within text

phrases indicating percentages

No Comments

No Known Activations