INDEX

Explanations

No Explanations Found

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

rive

-0.71

appropriately

-0.67

 Scal

-0.62

 Pell

-0.61

ritch

-0.61

 Gund

-0.61

iffe

-0.59

 Cosmos

-0.59

 Fernand

-0.59

 Cour

-0.59

POSITIVE LOGITS

insk

0.95

imoto

0.81

Joined

0.81

uten

0.81

Edited

0.76

IFE

0.72

actionDate

0.72

achelor

0.72

esan

0.71

stanbul

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.