INDEX

Explanations

phrases related to legal or regulatory frameworks

oai_token-act-pair · gpt-3.5-turbo

the phrase "Under" followed by various numerical levels, indicating regulations or rules

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

aukee

-0.83

bernatorial

-0.75

-0.71

 Scand

-0.64

 eternity

-0.63

ãĥ£

-0.61

astical

-0.60

atial

-0.60

apon

-0.58

 hereafter

-0.58

POSITIVE LOGITS

neath

1.26

lying

1.16

graduate

0.98

cover

0.94

itialized

0.92

Ļ½

0.91

pins

0.91

comings

0.90

stant

0.89

lining

0.87

Activations Density 0.023%

phrases related to legal or regulatory frameworks

the phrase "Under" followed by various numerical levels, indicating regulations or rules

No Comments

No Known Activations