INDEX

Explanations

phrases related to popular figures or personalities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Koster" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ccording

-0.80

ĵĺ

-0.80

trak

-0.71

 princ

-0.68

ournal

-0.66

Ĥª

-0.66

 ILCS

-0.66

uries

-0.64

andro

-0.63

isters

-0.63

POSITIVE LOGITS

oster

1.13

pole

0.93

oids

0.74

holm

0.74

eers

0.73

eer

0.72

bral

0.71

aceae

0.71

swick

0.71

oid

0.71

Activations Density 0.007%

phrases related to popular figures or personalities

occurrences of the word "Koster" and its variations

No Comments

No Known Activations