INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

FFER

-0.67

rose

-0.66

 sacrific

-0.65

BRE

-0.65

iffe

-0.65

ffield

-0.65

 miscar

-0.65

 contrasts

-0.65

 Vaugh

-0.65

 substituted

-0.64

POSITIVE LOGITS

Eco

0.67

Ace

0.67

chall

0.66

helle

0.64

peed

0.64

ibly

0.63

GMT

0.63

ateur

0.63

tails

0.63

 Globe

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.