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

gdala

-0.77

llah

-0.71

 jung

-0.65

ailable

-0.65

 Hockey

-0.63

tein

-0.63

Buff

-0.62

Plot

-0.62

ventory

-0.62

 defe

-0.61

POSITIVE LOGITS

onder

0.71

olen

0.69

asma

0.68

ush

0.68

uj

0.67

atcher

0.67

etheless

0.67

heed

0.67

istor

0.65

vernment

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.