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

Negative Logits

gard

-0.80

¥µ

-0.73

©¶æ¥µ

-0.70

gart

-0.68

PI

-0.68

ª

-0.67

å¹

-0.66

phil

-0.64

 Whis

-0.64

ndra

-0.64

POSITIVE LOGITS

ogue

0.76

agra

0.72

 sexes

0.71

herent

0.70

acci

0.67

 respectively

0.67

arity

0.65

yg

0.65

igne

0.64

 Mehran

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.