INDEX

Explanations

years mentioned in the text, specifically focusing on the year 2006

oai_token-act-pair · gpt-3.5-turbo

references to the year 2006

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

ding

-0.77

inances

-0.73

estine

-0.73

amins

-0.72

encers

-0.72

ances

-0.71

adata

-0.68

encer

-0.68

ende

-0.68

ritten

-0.68

POSITIVE LOGITS

teenth

0.88

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.83

0.78

NetMessage

0.71

assetsadobe

0.71

 partName

0.70

ocalyptic

0.67

------------------------------------------------

0.66

cture

0.65

Activations Density 0.024%

years mentioned in the text, specifically focusing on the year 2006

references to the year 2006

No Comments

No Known Activations