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

pmwiki

-0.82

 Spiegel

-0.74

itiz

-0.65

 lottery

-0.65

Ruk

-0.64

ãĤ¼

-0.61

 exits

-0.58

irlf

-0.58

itaire

-0.58

 Tina

-0.57

POSITIVE LOGITS

iasis

0.84

ornia

0.73

riv

0.69

artisan

0.66

ackets

0.66

interstitial

0.65

rils

0.65

este

0.64

indal

0.63

folk

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.