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

ãĤ«

-0.79

coe

-0.72

Topic

-0.72

chwitz

-0.71

yrinth

-0.69

rador

-0.68

cot

-0.67

gob

-0.66

artment

-0.66

BUG

-0.66

POSITIVE LOGITS

 Miko

0.72

rolled

0.66

folk

0.65

 Bale

0.62

 Breath

0.61

 sued

0.60

 karma

0.60

 Samson

0.60

 Rothschild

0.60

 regulators

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.