INDEX

Explanations

No Explanations Found

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

steen

-0.80

ezvous

-0.79

 Dwell

-0.78

vous

-0.76

ingham

-0.74

vana

-0.71

ships

-0.70

knit

-0.66

esse

-0.66

audio

-0.66

POSITIVE LOGITS

nesty

0.76

ife

0.74

Removed

0.73

 Calder

0.72

///

0.70

[/

0.66

 Nicol

0.63

 âĢķ

0.62

anda

0.61

thora

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.