INDEX

Explanations

mentions of political figures

oai_token-act-pair · gpt-3.5-turbo

references to political representatives

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

DragonMagazine

-0.70

glers

-0.70

ahime

-0.70

 underpin

-0.67

phal

-0.61

 Belfast

-0.59

 Gleaming

-0.58

bul

-0.56

)=(

-0.55

 Siberian

-0.55

POSITIVE LOGITS

orters

1.50

orter

1.44

rint

1.36

utation

1.25

orted

1.22

rieve

1.22

resents

1.15

ository

1.14

utable

1.09

atri

1.07

Activations Density 0.024%

mentions of political figures

references to political representatives

No Comments

No Known Activations