INDEX

Explanations

phrases related to contentious or controversial topics or opinions

oai_token-act-pair · gpt-3.5-turbo

topics related to social issues and cultural perceptions

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

eatures

-0.65

swick

-0.59

 VIDEOS

-0.59

ggles

-0.58

 redes

-0.56

 confir

-0.55

arthed

-0.54

acia

-0.53

everal

-0.53

OTOS

-0.53

POSITIVE LOGITS

 because

1.09

 somehow

1.08

 unfairly

1.03

 rather

0.96

?,

0.95

 anymore

0.94

 whereas

0.90

or

0.89

 despite

0.87

 deserving

0.86

Activations Density 0.490%

phrases related to contentious or controversial topics or opinions

topics related to social issues and cultural perceptions

No Comments

No Known Activations