INDEX

Explanations

names of political figures

oai_token-act-pair · gpt-3.5-turbo

names of political figures and their respective mentions in the text

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

Negative Logits

MSI

-0.67

Cth

-0.66

ĸļ

-0.65

VID

-0.64

 Scandinavian

-0.63

EVE

-0.60

 Fres

-0.57

AVG

-0.57

 captcha

-0.56

 Unicode

-0.55

POSITIVE LOGITS

 vowed

0.99

 campaigned

0.99

 aides

0.96

 announces

0.91

 vows

0.91

 accuses

0.90

 proposes

0.90

 tweeted

0.89

 promised

0.89

 vetoed

0.88

Activations Density 0.191%

names of political figures

names of political figures and their respective mentions in the text

No Known Activations