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

Wra

-0.74

tch

-0.73

 unloaded

-0.69

 submer

-0.65

 Cutter

-0.64

 Archangel

-0.64

Pap

-0.63

 touched

-0.62

Cop

-0.62

tymology

-0.62

POSITIVE LOGITS

ãĤ«

0.77

 guiName

0.71

 drafting

0.68

orescence

0.68

 STATES

0.68

ãĥĲ

0.67

 Guilty

0.64

CLA

0.63

hibition

0.63

 WHERE

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.