INDEX

Explanations

locations or addresses, particularly in the United States

oai_token-act-pair · gpt-3.5-turbo

geographical locations and their corresponding states or regions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

lihood

-0.87

henko

-0.72

andowski

-0.70

ufact

-0.68

mania

-0.66

Proof

-0.66

Afee

-0.65

toggle

-0.64

ãĤ¨ãĥ«

-0.64

loads

-0.63

POSITIVE LOGITS

./

0.69

 Supervisor

0.68

 Dept

0.65

achusetts

0.64

 tradem

0.64

ARA

0.61

ithing

0.61

ometown

0.60

 subur

0.60

 STATE

0.59

Activations Density 0.036%

locations or addresses, particularly in the United States

geographical locations and their corresponding states or regions

No Known Activations