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

aer

-0.72

alez

-0.69

 istg

-0.69

ento

-0.68

aday

-0.65

cap

-0.64

Aly

-0.64

 unsolved

-0.62

 fortun

-0.62

adder

-0.62

POSITIVE LOGITS

PT

0.83

 CLSID

0.79

selection

0.71

 Crusade

0.68

 EDITION

0.68

 Knowledge

0.63

anu

0.62

PsyNetMessage

0.62

XV

0.60

DCS

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.