INDEX

Explanations

political figures' names

oai_token-act-pair · gpt-3.5-turbo

names of prominent political figures

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

 Mehran

-0.61

semble

-0.59

 posted

-0.58

 streamed

-0.58

ASA

-0.57

 Veter

-0.57

 Honolulu

-0.56

 Indianapolis

-0.56

 Norn

-0.55

 Captain

-0.55

POSITIVE LOGITS

omics

1.30

mania

1.17

ism

1.10

ian

1.06

esque

1.05

care

1.02

isms

0.95

Care

0.94

itism

0.94

istas

0.86

Activations Density 0.232%

political figures' names

names of prominent political figures

No Comments

No Known Activations