INDEX

Explanations

acronyms related to companies and organizations

oai_token-act-pair · gpt-3.5-turbo

references to specific organizations or companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

lihood

-0.78

lings

-0.72

saf

-0.71

soever

-0.69

=\"

-0.69

ibility

-0.68

Pwr

-0.63

gew

-0.63

 contrary

-0.62

na

-0.62

POSITIVE LOGITS

CO

1.30

OPER

0.93

xon

0.92

CO

0.91

CHR

0.84

leans

0.82

oS

0.81

verage

0.81

ffee

0.80

perty

0.79

Activations Density 0.004%

acronyms related to companies and organizations

references to specific organizations or companies

No Comments

No Known Activations