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

 pent

-0.66

 Browne

-0.60

 damned

-0.58

TRUMP

-0.58

 vulner

-0.58

cler

-0.58

antly

-0.58

voc

-0.57

 legitim

-0.57

 Debor

-0.57

POSITIVE LOGITS

ĻĤ

1.10

isode

0.97

 guiActiveUn

0.83

hedral

0.81

»Ĵ

0.76

reetings

0.74

ovie

0.74

ĪĴ

0.74

yip

0.73

 spac

0.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.