INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 uniqueness

-0.72

 exceptional

-0.65

 creation

-0.64

 Advent

-0.63

tun

-0.62

 independence

-0.62

iqueness

-0.62

creation

-0.61

)",

-0.61

IPP

-0.61

POSITIVE LOGITS

tics

1.13

tic

0.85

adays

0.76

abouts

0.76

mos

0.71

ricting

0.70

Ĥİ

0.69

byss

0.68

cific

0.68

 Thro

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.