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

ateur

-0.79

atell

-0.73

arton

-0.69

AAC

-0.68

itars

-0.66

$$

-0.66

utterstock

-0.66

$$

-0.64

Intern

-0.63

idepress

-0.62

POSITIVE LOGITS

 Rune

0.66

 defences

0.64

 rune

0.64

 Hero

0.63

 reckoning

0.62

 Myanmar

0.61

dragon

0.61

raid

0.60

 Surge

0.60

 HERO

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.