INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

FINE

-0.70

 Guid

-0.69

 Borders

-0.67

 repayment

-0.66

 calculation

-0.64

 refunds

-0.62

ortium

-0.60

 reprint

-0.60

 footnote

-0.60

 Seller

-0.60

POSITIVE LOGITS

iru

0.94

raviolet

0.88

udos

0.86

rex

0.84

oppable

0.80

vik

0.77

zona

0.76

rued

0.76

marine

0.75

enic

0.75

Activations Density 0.000%

No Known Activations

This feature has no known activations.