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

puter

-0.77

ŃĶ

-0.72

uph

-0.70

VOL

-0.70

Dragon

-0.69

ibble

-0.69

unic

-0.68

eva

-0.67

istor

-0.67

ube

-0.66

POSITIVE LOGITS

images

0.70

 correl

0.69

pac

0.66

atic

0.64

 views

0.64

 appendix

0.63

icultural

0.62

displayText

0.62

izon

0.61

aneers

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.