INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

©¶æ

-0.82

KM

-0.75

Topics

-0.73

KP

-0.68

Īè

-0.67

nz

-0.63

 Luthor

-0.63

 Cortex

-0.62

rgb

-0.62

Ns

-0.62

POSITIVE LOGITS

agher

0.72

 Indust

0.72

itness

0.70

raught

0.70

 Shay

0.68

gotten

0.68

Accessory

0.68

venge

0.68

emale

0.64

 attest

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.