INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Cosponsors

-0.80

estones

-0.77

tek

-0.76

sburg

-0.74

pas

-0.73

Reviewer

-0.72

Found

-0.72

itte

-0.71

uyomi

-0.71

Place

-0.71

POSITIVE LOGITS

 Hath

0.68

 disregard

0.65

 Chandra

0.65

 alignment

0.63

 displacement

0.62

 ordering

0.62

 confirmation

0.60

 anything

0.60

 corrective

0.60

 phenomenal

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.