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

ALSE

-0.72

coh

-0.69

ophon

-0.67

successful

-0.66

 Invention

-0.64

 Ampl

-0.64

ovember

-0.63

aneers

-0.63

ochond

-0.62

ocent

-0.62

POSITIVE LOGITS

itcher

0.68

asca

0.67

metadata

0.67

info

0.65

capacity

0.64

 Gors

0.64

ranking

0.63

arella

0.63

lycer

0.62

lance

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.