INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

itialized

-0.72

irm

-0.72

 Leigh

-0.68

Sph

-0.67

 Hait

-0.66

 defic

-0.66

 Remastered

-0.64

 Beir

-0.64

Ó

-0.63

ADRA

-0.62

POSITIVE LOGITS

cius

0.81

icles

0.80

conom

0.76

metal

0.74

icle

0.71

hattan

0.70

FORE

0.67

 jewels

0.64

gas

0.63

DER

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.