INDEX

Explanations

mentions of the word "Hunt" or variations of it

oai_token-act-pair · gpt-3.5-turbo

variations of the word "hunting."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 subtract

-0.66

 Birch

-0.64

 Colossus

-0.64

 compliment

-0.63

 connecting

-0.62

AGE

-0.62

 Mour

-0.62

oral

-0.62

toe

-0.61

 chloride

-0.61

POSITIVE LOGITS

ters

1.26

cheon

1.21

ches

1.08

ting

1.05

kered

1.01

sts

1.01

eteenth

1.01

zees

0.99

ãĤ§

0.98

ger

0.98

Activations Density 0.008%

mentions of the word "Hunt" or variations of it

variations of the word "hunting."

No Comments

No Known Activations