INDEX

Explanations

names of political leaders and government officials

oai_token-act-pair · gpt-3.5-turbo

uppercase initials or single-letter abbreviations that likely represent names or titles

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Rebels

-0.73

 Echoes

-0.67

 Forsaken

-0.66

 battleground

-0.66

 captcha

-0.65

 womb

-0.64

 Californ

-0.63

 Cerberus

-0.63

 Rebellion

-0.62

 recapt

-0.61

POSITIVE LOGITS

ona

1.06

isha

1.03

dan

1.00

aby

0.97

leen

0.97

uel

0.96

rak

0.95

ika

0.92

ifa

0.91

iel

0.90

Activations Density 0.210%

names of political leaders and government officials

uppercase initials or single-letter abbreviations that likely represent names or titles

No Known Activations