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

ĸļ

-0.90

 millenn

-0.82

cknow

-0.75

pora

-0.72

¥ŀ

-0.72

 tremend

-0.71

DonaldTrump

-0.71

fuck

-0.70

uph

-0.69

 tiss

-0.69

POSITIVE LOGITS

 Conce

0.73

âĢ²

0.73

 Firearms

0.72

 Choice

0.69

 Weed

0.67

 Classification

0.66

QC

0.66

 DevOnline

0.65

 Grass

0.65

 Fishing

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.