INDEX

Explanations

mentions of the word "Camp"

oai_token-act-pair · gpt-3.5-turbo

mentions of "Camp" followed by various designations or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 magnification

-0.75

 platinum

-0.66

 pulse

-0.66

 regress

-0.63

 Marketable

-0.61

rencies

-0.60

raught

-0.60

insured

-0.59

à¥

-0.59

 redistributed

-0.58

POSITIVE LOGITS

 Camp

1.30

camp

1.27

Camp

1.16

agna

0.97

bell

0.95

 camp

0.91

ground

0.90

ovie

0.90

aign

0.89

ione

0.82

Activations Density 0.007%

mentions of the word "Camp"

mentions of "Camp" followed by various designations or locations

No Comments

No Known Activations