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

ItemTracker

-0.82

requency

-0.78

illin

-0.73

arching

-0.72

scan

-0.69

chlor

-0.69

wana

-0.69

uka

-0.68

ãĤ®

-0.68

 Commodore

-0.68

POSITIVE LOGITS

 millenn

0.81

 concede

0.71

arent

0.71

 unden

0.69

hug

0.67

 semblance

0.65

 gesture

0.64

act

0.63

 sacrific

0.63

 Estate

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.