INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Hitch

-0.76

 Seat

-0.72

 captcha

-0.70

 VIDE

-0.70

-0.68

 whiff

-0.64

 Quartz

-0.61

iP

-0.61

 rapp

-0.60

 herd

-0.60

POSITIVE LOGITS

oyer

0.91

tions

0.84

tion

0.80

dor

0.72

ten

0.68

Ã©n

0.68

ajo

0.67

Tu

0.66

indal

0.66

prof

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.