INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

izons

-0.74

 uncertainty

-0.74

irlf

-0.71

efficients

-0.71

uala

-0.70

 uncertainties

-0.68

elight

-0.68

 upheaval

-0.67

 bott

-0.67

 whistleblower

-0.67

POSITIVE LOGITS

 Hath

0.73

ledged

0.73

:=

0.73

.-

0.65

bernatorial

0.64

iris

0.63

Serv

0.62

ciation

0.62

 Guarant

0.61

GH

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.