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

Negative Logits

 cents

-0.67

NA

-0.66

DCS

-0.64

 penn

-0.63

ORN

-0.59

Fed

-0.58

Â¢

-0.58

west

-0.58

ULE

-0.57

HRC

-0.57

POSITIVE LOGITS

acan

0.70

llah

0.68

iggs

0.67

 veter

0.66

ynski

0.65

rul

0.65

rien

0.64

 juven

0.64

orius

0.64

igsaw

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.