INDEX

Explanations

mentions of the name "Barack Obama."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Barack Obama."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

wagen

-0.74

âķĲ

-0.73

yss

-0.72

ategory

-0.70

pel

-0.68

âķĲâķĲ

-0.68

 jelly

-0.66

srf

-0.66

TOR

-0.66

pmwiki

-0.63

POSITIVE LOGITS

 Obama

1.22

 Hussein

1.15

Obama

0.97

 Barack

0.96

 Glenn

0.88

 Lyndon

0.85

 Trudeau

0.79

ration

0.79

 Reagan

0.78

ufact

0.78

Activations Density 0.012%

mentions of the name "Barack Obama."

occurrences of the name "Barack Obama."

No Known Activations