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

amsung

-0.87

 Tradable

-0.70

Requires

-0.70

 Everywhere

-0.68

Amp

-0.66

odies

-0.66

ASE

-0.65

udo

-0.65

 Ampl

-0.65

 Permanent

-0.65

POSITIVE LOGITS

itars

0.73

stery

0.67

uel

0.66

 launchers

0.61

 Kron

0.61

 comr

0.61

 mamm

0.61

 exodus

0.61

 favour

0.60

rou

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.