INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

olean

-0.67

 Slater

-0.66

 Patt

-0.64

nant

-0.63

enegger

-0.63

ido

-0.63

 Fritz

-0.63

 Hastings

-0.62

 Sullivan

-0.61

 Carey

-0.61

POSITIVE LOGITS

ibrary

0.69

 razor

0.64

Ħ¢

0.63

division

0.63

 eyed

0.63

 langu

0.62

 expiration

0.61

 denomin

0.60

 thorn

0.60

 pupil

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.