INDEX

Explanations

locations or addresses

oai_token-act-pair · gpt-3.5-turbo

geographical locations and institutions associated with research or events

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

 Finder

-0.79

 mercy

-0.62

 tyre

-0.60

opic

-0.59

 metre

-0.59

 skelet

-0.59

 Hubble

-0.58

gamer

-0.57

 precedence

-0.57

Ps

-0.56

POSITIVE LOGITS

 Heights

1.12

TX

0.99

 Calif

0.97

 Junction

0.96

 Township

0.96

OH

0.93

 suburb

0.90

hurst

0.89

 Springs

0.88

shire

0.88

Activations Density 0.214%

locations or addresses

geographical locations and institutions associated with research or events

No Comments

No Known Activations