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

 clipping

-0.76

 occas

-0.76

ertodd

-0.76

 Antar

-0.69

assic

-0.67

culosis

-0.65

ruciating

-0.65

 interrogation

-0.64

entimes

-0.63

ciating

-0.61

POSITIVE LOGITS

FAA

0.71

amus

0.70

hold

0.69

 Revis

0.68

Coh

0.67

 Demo

0.67

 Stout

0.67

Blu

0.65

EDT

0.64

BRE

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.