INDEX

Explanations

word sequences related to legal and legislative actions

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate proposed changes or amendments in legislation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

rete

-0.72

UGH

-0.72

notice

-0.71

 sqor

-0.71

oad

-0.69

ovo

-0.67

omatic

-0.64

hift

-0.64

OX

-0.63

live

-0.63

POSITIVE LOGITS

 prohibits

1.20

 forbids

1.12

 restricts

1.10

 bans

1.09

 governs

1.08

 regulates

1.05

 seeks

1.00

 legalized

0.99

 prevents

0.97

 decriminal

0.97

Activations Density 0.107%

word sequences related to legal and legislative actions

phrases that indicate proposed changes or amendments in legislation

No Comments

No Known Activations