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

-0.92

ivating

-0.86

¥ŀ

-0.81

 triv

-0.77

 mathemat

-0.75

*/(

-0.73

rug

-0.73

 explan

-0.72

etheless

-0.71

 pillar

-0.71

POSITIVE LOGITS

Check

0.90

features

0.89

Serial

0.81

Buy

0.80

Case

0.79

credit

0.79

Attack

0.76

Jones

0.76

Join

0.75

default

0.75

Activations Density 0.000%

No Known Activations

This feature has no known activations.