INDEX

Explanations

references to the specific term "Hol" or "Hol" followed by another word

oai_token-act-pair · gpt-3.5-turbo

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

 Lowell

-0.70

ITAL

-0.68

EED

-0.66

REE

-0.66

Pool

-0.64

 Strauss

-0.61

 responsible

-0.60

 Elon

-0.59

 inhibitor

-0.58

 inhibitors

-0.58

POSITIVE LOGITS

ocaust

1.46

idays

1.40

iday

1.36

ocene

1.34

oho

1.06

isky

1.03

stery

1.03

comb

1.00

ophon

0.99

mberg

0.98

Activations Density 0.035%

references to the specific term "Hol" or "Hol" followed by another word

No Comments

No Known Activations