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

stellar

-0.74

 Juno

-0.74

science

-0.73

 Lies

-0.71

 Sequ

-0.70

 Judith

-0.68

 Written

-0.66

 Vale

-0.65

 Doct

-0.65

 Soda

-0.64

POSITIVE LOGITS

agos

0.78

apter

0.76

ASC

0.74

akh

0.73

aldo

0.73

 sqor

0.72

 Expand

0.71

ilit

0.70

ajor

0.69

uras

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.