INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

aturdays

-0.84

awaru

-0.81

quished

-0.80

cano

-0.77

llah

-0.73

 toget

-0.72

iltration

-0.72

aters

-0.71

CLASSIFIED

-0.69

yright

-0.69

POSITIVE LOGITS

smith

0.73

 Kund

0.71

CMS

0.69

 Malta

0.64

 Portugal

0.64

 Karn

0.64

 Leone

0.63

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.62

 Maced

0.61

 Liberia

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.