INDEX

Explanations

locations described with details like "located in," "situated in," or "on the top of."

oai_token-act-pair · gpt-3.5-turbo

locations and geographical descriptions in text

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

uploads

-0.65

 unborn

-0.63

chio

-0.63

selves

-0.60

 delivered

-0.59

videos

-0.59

 worms

-0.58

acer

-0.58

 helper

-0.58

gram

-0.57

POSITIVE LOGITS

 footh

0.98

 downtown

0.93

 scenic

0.92

 northwest

0.88

 southwest

0.88

 Historic

0.86

 intersection

0.86

 northeast

0.85

 suburb

0.85

rium

0.84

Activations Density 0.182%

locations described with details like "located in," "situated in," or "on the top of."

locations and geographical descriptions in text

No Comments

No Known Activations