INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

rage

-1.00

asts

-0.89

gdala

-0.79

ufact

-0.75

iphate

-0.73

pel

-0.73

ayers

-0.72

ÄŁ

-0.69

phrine

-0.67

liga

-0.66

POSITIVE LOGITS

RFC

0.66

pH

0.62

ãĥ³ãĤ¸

0.62

uyomi

0.60

recated

0.60

 fluoride

0.60

PLIED

0.57

 millisec

0.56

 trademark

0.56

URI

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.