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

Ĥİ

-0.74

 Preservation

-0.73

agate

-0.69

 subsequ

-0.69

Write

-0.65

bone

-0.64

kamp

-0.63

hyde

-0.62

 relation

-0.62

 shape

-0.62

POSITIVE LOGITS

raphics

0.91

é¾

0.86

ä¸ī

0.80

irgin

0.77

 Cosponsors

0.75

mp

0.75

estic

0.74

ãĥĦ

0.72

STDOUT

0.72

irling

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.