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

wark

-0.78

scape

-0.68

 Armageddon

-0.64

veyard

-0.64

 Rousse

-0.63

ted

-0.62

ACTION

-0.61

eping

-0.61

 millenn

-0.61

bage

-0.61

POSITIVE LOGITS

Downloadha

0.76

answered

0.67

imon

0.65

 Â¶

0.64

CG

0.64

MFT

0.64

Ohio

0.63

ALD

0.63

 Topics

0.62

[&

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.