INDEX

Explanations

mentions of the word "constitutional" and related terms

oai_token-act-pair · gpt-3.5-turbo

references to constitutional concepts and legal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

paces

-0.74

 Shed

-0.74

ages

-0.72

yang

-0.72

DAQ

-0.71

elsen

-0.70

Merc

-0.70

 anecd

-0.70

hammad

-0.69

BALL

-0.69

POSITIVE LOGITS

 amendment

1.06

 monarchy

1.02

 amendments

1.01

 rights

0.98

 Amendments

0.98

 Amendment

0.97

 violations

0.95

 protections

0.95

 validity

0.92

 violation

0.91

Activations Density 0.018%

mentions of the word "constitutional" and related terms

references to constitutional concepts and legal issues

No Comments

No Known Activations