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

 Cere

-0.75

 Panc

-0.75

 Networks

-0.68

opsy

-0.64

 Models

-0.64

mails

-0.63

 Transformation

-0.63

oop

-0.63

 Handling

-0.62

Rew

-0.62

POSITIVE LOGITS

CHAT

0.70

imes

0.69

prus

0.67

ure

0.66

 pocket

0.66

 cryptoc

0.66

 humour

0.64

ongyang

0.64

ipeg

0.62

ãĥ¯ãĥ³

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.