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

half

-0.63

Leaks

-0.62

 Gree

-0.61

¬¼

-0.60

ISTER

-0.59

secution

-0.58

 neighbour

-0.58

 Cree

-0.58

 Parliamentary

-0.58

LOAD

-0.57

POSITIVE LOGITS

thood

0.78

inion

0.74

ythm

0.74

vim

0.70

otonin

0.70

ino

0.67

angan

0.67

ëĭ

0.61

Þ

0.59

wcsstore

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.