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

MpServer

-0.74

 cryptoc

-0.68

retty

-0.67

earch

-0.67

ients

-0.66

irie

-0.65

versions

-0.64

osate

-0.63

ridges

-0.62

 Pict

-0.62

POSITIVE LOGITS

 lodge

0.81

 Gott

0.73

 Everett

0.68

 vict

0.65

 haunt

0.63

 Freddy

0.63

otte

0.63

Hed

0.62

 existence

0.61

tor

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.