INDEX

Explanations

phrases related to laws, regulations, and legal actions

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases indicating legal contexts or regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

twitch

-0.78

================================

-0.70

Voice

-0.68

fuck

-0.68

onica

-0.67

amily

-0.66

########

-0.66

ãĥ³ãĤ¸

-0.66

itans

-0.65

ãĤĵ

-0.65

POSITIVE LOGITS

 thereby

1.02

 prohibits

0.93

 forbids

0.86

 subjected

0.83

 eliminates

0.83

 recommends

0.83

 imposes

0.83

 thereafter

0.81

 restricts

0.81

 prohibit

0.80

Activations Density 0.408%

phrases related to laws, regulations, and legal actions

conjunctions and phrases indicating legal contexts or regulations

No Comments

No Known Activations