INDEX

Explanations

words related to academic or technical whitepapers

oai_token-act-pair · gpt-3.5-turbo

variations of the prefix "whit" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

)=(

-0.79

 Scand

-0.69

 surg

-0.69

 Trin

-0.68

Zur

-0.68

 Inquis

-0.66

Jur

-0.65

 Kinnikuman

-0.65

 epid

-0.65

 Amen

-0.65

POSITIVE LOGITS

oop

1.04

akers

1.02

ocket

1.00

ooth

0.97

oops

0.95

oggle

0.95

akes

0.94

arter

0.94

ound

0.94

oths

0.94

Activations Density 0.173%

words related to academic or technical whitepapers

variations of the prefix "whit" and related terms

No Comments

No Known Activations