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

ciating

-0.77

agram

-0.67

joy

-0.67

bon

-0.64

 statue

-0.62

Buc

-0.62

 semblance

-0.62

ansas

-0.62

brown

-0.61

buck

-0.61

POSITIVE LOGITS

llah

0.77

TD

0.75

MPG

0.70

inventoryQuantity

0.68

aspers

0.67

APR

0.67

CLASSIFIED

0.66

erness

0.64

TeX

0.64

IPS

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.