INDEX

Explanations

phrases related to freedom of speech

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of free speech

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

 Hitch

-0.71

xon

-0.68

AMI

-0.65

Mig

-0.65

erald

-0.64

cit

-0.63

 Dani

-0.63

 Lans

-0.62

hin

-0.61

 Benz

-0.61

POSITIVE LOGITS

 rights

1.16

 freedoms

1.10

 protections

1.08

rights

1.02

 Rights

1.01

speech

0.95

 advocates

0.92

 violations

0.90

 freedom

0.87

 liberties

0.87

Activations Density 0.093%

phrases related to freedom of speech

phrases related to the concept of free speech

No Comments

No Known Activations