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

agy

-0.72

istani

-0.71

ondo

-0.71

asonic

-0.68

xon

-0.66

onomic

-0.66

agara

-0.66

assic

-0.64

ilateral

-0.64

kefeller

-0.63

POSITIVE LOGITS

 Machina

0.87

NetMessage

0.77

Ã¼r

0.68

=]

0.67

 Chimera

0.67

 Vance

0.66

GES

0.66

 newcom

0.66

drm

0.66

 COVER

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.