INDEX

Explanations

phrases related to legal punishments or sentences

oai_token-act-pair · gpt-3.5-turbo

phrases indicating legal penalties or sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

illin

-0.91

soType

-0.83

ern

-0.80

edin

-0.78

DragonMagazine

-0.75

Craft

-0.75

atl

-0.74

LAB

-0.74

unny

-0.73

bleacher

-0.72

POSITIVE LOGITS

 violating

0.97

gery

0.96

 breaching

0.93

 questioning

0.91

geries

0.89

aging

0.87

 committing

0.84

 daring

0.83

 accessing

0.83

bidden

0.82

Activations Density 0.144%

phrases related to legal punishments or sentences

phrases indicating legal penalties or sentences

No Comments

No Known Activations