INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Renew

-0.68

ãĥ´

-0.67

 recomm

-0.65

 rehe

-0.64

essim

-0.64

OPA

-0.63

hov

-0.62

quel

-0.62

rica

-0.61

 rece

-0.61

POSITIVE LOGITS

fman

0.76

heads

0.73

 carts

0.69

avorite

0.69

 Bundy

0.69

ipple

0.68

yip

0.68

doms

0.65

Fu

0.65

arge

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.