INDEX

Explanations

mentions of the word "Zero"

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Zero" and its related 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

owship

-0.85

sbm

-0.83

worldly

-0.77

antly

-0.75

details

-0.74

aign

-0.74

ammed

-0.74

atural

-0.74

ammad

-0.72

amental

-0.72

POSITIVE LOGITS

Zero

0.95

MQ

0.83

 Zero

0.83

Draft

0.81

 Tone

0.75

 Lounge

0.74

 Fighters

0.72

BSD

0.72

 Dwell

0.71

 Suit

0.71

Activations Density 0.037%

mentions of the word "Zero"

mentions of the term "Zero" and its related variations

No Comments

No Known Activations