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

Heb

-0.68

 meters

-0.63

 simulated

-0.63

imar

-0.63

von

-0.61

 Fran

-0.60

cia

-0.60

 aber

-0.60

ivably

-0.58

yz

-0.58

POSITIVE LOGITS

PLA

0.81

 Browse

0.70

 THANK

0.69

Commerce

0.68

ENE

0.67

 Percent

0.67

REL

0.67

orage

0.66

anooga

0.66

VALUE

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.