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

ingen

-0.76

¥µ

-0.73

Ñĭ

-0.71

Berry

-0.70

advertisement

-0.70

 Rivers

-0.69

ĪĴ

-0.67

atos

-0.66

 srfAttach

-0.65

atever

-0.64

POSITIVE LOGITS

 attribution

0.81

 framing

0.73

 magnitude

0.73

 pand

0.73

 acronym

0.72

 target

0.69

 designation

0.68

 lows

0.68

velength

0.68

 targets

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.