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

paces

-0.81

afort

-0.78

externalActionCode

-0.76

 Ambro

-0.75

 graz

-0.72

baugh

-0.71

etts

-0.70

qua

-0.69

trak

-0.68

 seizures

-0.67

POSITIVE LOGITS

league

0.77

bery

0.74

Export

0.69

Roger

0.69

Ãī

0.69

ender

0.68

bye

0.65

Prem

0.63

ordes

0.62

enders

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.