INDEX

Explanations

measurements expressed in millimeters (mm) with a high activation value

oai_token-act-pair · gpt-3.5-turbo

measurements of distance and weight

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

bidden

-0.78

adobe

-0.75

artist

-0.72

vale

-0.71

terday

-0.71

idate

-0.71

eer

-0.68

tenance

-0.68

gotten

-0.67

Dub

-0.66

POSITIVE LOGITS

km

0.80

kg

0.79

 diameter

0.78

icka

0.75

ocular

0.73

 Cheong

0.72

EDT

0.71

 submerged

0.70

 watt

0.70

 spacing

0.69

Activations Density 0.039%

measurements expressed in millimeters (mm) with a high activation value

measurements of distance and weight

No Comments

No Known Activations