INDEX

Explanations

abbreviated organizations and their respective authorities

oai_token-act-pair · gpt-3.5-turbo

acronyms or parentheses used in organizational names and agencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ãĥĦ

-0.75

ãĥ´ãĤ¡

-0.75

worldly

-0.73

ãĥĥãĥī

-0.68

ãĥ¥

-0.68

ãĥ«

-0.68

Ļ½

-0.66

wcs

-0.66

 answ

-0.65

spo

-0.64

POSITIVE LOGITS

Ltd

0.66

 Syndicate

0.66

 Certification

0.63

 Construct

0.62

 Cooperative

0.60

 Limited

0.60

 designation

0.58

insured

0.58

 Award

0.58

psey

0.58

Activations Density 0.088%

abbreviated organizations and their respective authorities

acronyms or parentheses used in organizational names and agencies

No Comments

No Known Activations