INDEX

Explanations

numerical values

oai_token-act-pair · gpt-3.5-turbo

specific numeric values or quantifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

sonian

-0.69

Osw

-0.68

dinand

-0.67

enegger

-0.67

 cout

-0.62

 tidal

-0.60

 dumps

-0.60

 cryptoc

-0.60

shire

-0.59

 landmark

-0.59

POSITIVE LOGITS

cia

0.95

 Flavoring

0.88

oire

0.73

aria

0.71

render

0.70

oft

0.70

yet

0.70

Minecraft

0.69

Filter

0.69

ide

0.68

Activations Density 0.000%

numerical values

specific numeric values or quantifications

No Comments

No Known Activations