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

edi

-0.78

zynski

-0.74

llular

-0.68

gn

-0.68

chwitz

-0.67

cki

-0.66

utic

-0.66

brid

-0.65

ogo

-0.64

oshi

-0.64

POSITIVE LOGITS

 ãĤ

0.81

 annex

0.69

âĶĢâĶĢâĶĢâĶĢ

0.69

 medd

0.68

*/(

0.66

 ÙĪ

0.66

 Agency

0.65

"}],"

0.65

Sit

0.63

––

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.