INDEX

Explanations

mentions of political figures and government officials

oai_token-act-pair · gpt-3.5-turbo

political or government-related names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

iencies

-0.73

abases

-0.62

 havoc

-0.62

 distinctions

-0.61

 yuan

-0.57

aido

-0.56

lder

-0.55

 bets

-0.54

 distinction

-0.54

 burgers

-0.54

POSITIVE LOGITS

 informing

1.14

 stating

1.13

 indicating

1.12

 outlining

1.11

 detailing

1.11

 wherein

1.07

 concerning

1.06

 regarding

1.03

 Regarding

1.02

 describing

1.01

Activations Density 0.607%

mentions of political figures and government officials

political or government-related names and titles

No Comments

No Known Activations