INDEX

Explanations

informations related to uncertainty or change

oai_token-act-pair · gpt-3.5-turbo

words expressing states of uncertainty or conditions related to situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ago

-0.71

azo

-0.70

 Flavoring

-0.70

 NAME

-0.66

auer

-0.63

omething

-0.63

DragonMagazine

-0.63

èĪ

-0.62

odan

-0.61

otaur

-0.61

POSITIVE LOGITS

 asleep

0.90

 awake

0.78

 locked

0.75

ready

0.75

 poised

0.75

 unwilling

0.75

tow

0.74

 undis

0.74

 shaken

0.73

 ready

0.73

Activations Density 0.389%

informations related to uncertainty or change

words expressing states of uncertainty or conditions related to situations

No Comments

No Known Activations