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

taboola

-0.86

uble

-0.74

cheat

-0.70

rontal

-0.69

Tier

-0.68

--------------------------------------------------------

-0.66

ãĥ¥

-0.66

\\\\\\\\\\\\\\\\

-0.66

tein

-0.66

Seg

-0.66

POSITIVE LOGITS

iring

0.70

aganda

0.66

eva

0.65

pport

0.65

azi

0.63

 inviting

0.63

CHA

0.62

 Communism

0.61

attering

0.61

ontent

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.