INDEX

Explanations

phrases related to various positive or negative phenomena or characteristics

oai_token-act-pair · gpt-3.5-turbo

words associated with positive attributes or phenomena

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

yss

-0.66

Physical

-0.66

 withdrawing

-0.64

allic

-0.63

 withdrawn

-0.63

 sshd

-0.62

 administration

-0.60

ModLoader

-0.60

ãģį

-0.59

 Presbyterian

-0.59

POSITIVE LOGITS

 extraord

0.88

 fest

0.86

undrum

0.86

stros

0.84

hots

0.81

manac

0.76

 nightmare

0.76

yssey

0.76

 cele

0.75

icion

0.74

Activations Density 0.482%

phrases related to various positive or negative phenomena or characteristics

words associated with positive attributes or phenomena

No Comments

No Known Activations