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

 Metatron

-0.80

Font

-0.73

 Scheme

-0.73

 Byrne

-0.73

 Noir

-0.71

Adds

-0.68

 PAGE

-0.67

cz

-0.66

 Seller

-0.65

GV

-0.65

POSITIVE LOGITS

onyms

0.73

opter

0.69

duction

0.64

 Malays

0.62

 exert

0.61

iped

0.61

 hump

0.60

orne

0.60

 Potential

0.59

ritch

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.