INDEX

Explanations

locations or places mentioned in text

oai_token-act-pair · gpt-3.5-turbo

references to locations or geographical entities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

eus

-0.76

ifact

-0.73

STD

-0.72

ERA

-0.72

arians

-0.72

ality

-0.71

chrom

-0.69

each

-0.69

worthiness

-0.69

JUST

-0.68

POSITIVE LOGITS

 suburbs

1.53

 Bronx

1.41

 suburb

1.33

 outskirts

1.25

 vicinity

1.25

 city

1.22

 countryside

1.20

 borough

1.16

 basement

1.15

 neighborhood

1.15

Activations Density 0.166%

locations or places mentioned in text

references to locations or geographical entities

No Comments

No Known Activations