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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Paran

-0.76

IPM

-0.71

 Shelley

-0.65

 Dianne

-0.63

 broom

-0.63

 Heidi

-0.63

 Gardner

-0.61

 Susan

-0.60

Article

-0.60

 Sagan

-0.59

POSITIVE LOGITS

essa

0.85

ahl

0.78

ech

0.74

aff

0.74

psey

0.73

ead

0.72

 recol

0.68

earing

0.66

=#

0.65

ains

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.