INDEX

Explanations

diagrams or schematic representations

oai_token-act-pair · gpt-3.5-turbo

references to diagrams and schematics

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

 rainy

-0.73

NetMessage

-0.72

ierra

-0.66

Chance

-0.65

akening

-0.63

ushes

-0.61

intend

-0.61

 stronghold

-0.60

atton

-0.59

elope

-0.58

POSITIVE LOGITS

 diagram

1.10

matic

1.03

matically

1.03

 diagrams

1.02

ming

0.95

matical

0.91

azaki

0.85

zag

0.81

clip

0.78

Plex

0.78

Activations Density 0.011%

diagrams or schematic representations

references to diagrams and schematics

No Comments

No Known Activations