INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ructure

-0.75

dr

-0.61

redo

-0.61

 Erik

-0.59

 grips

-0.59

redits

-0.59

redit

-0.59

size

-0.59

VG

-0.58

 parcels

-0.58

POSITIVE LOGITS

 heard

1.69

heard

1.23

 Heard

1.02

 human

0.83

 guiActiveUn

0.79

Bey

0.76

 overheard

0.73

ĩ

0.73

 persuasive

0.72

Human

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.