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

udic

-0.84

ota

-0.71

apsed

-0.70

rower

-0.69

lies

-0.68

earance

-0.68

icular

-0.67

apses

-0.66

istries

-0.66

akeru

-0.65

POSITIVE LOGITS

OPA

0.61

 Hunts

0.60

 Harmony

0.60

 Helm

0.58

 Maid

0.56

 Pixie

0.56

IJ

0.56

 Bast

0.56

 Nobody

0.55

 Minotaur

0.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.