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

avorite

-0.76

oppy

-0.75

steen

-0.75

agher

-0.74

acebook

-0.74

Loading

-0.72

bidden

-0.71

ounty

-0.67

yip

-0.67

reet

-0.66

POSITIVE LOGITS

 Cousins

0.71

 Serbia

0.67

CES

0.65

yg

0.64

 Constantin

0.63

ven

0.63

 Rasm

0.63

Ov

0.60

 Croatia

0.60

 Rafael

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.