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

anwhile

-0.68

urst

-0.68

ammed

-0.67

apan

-0.65

occup

-0.65

 Reborn

-0.64

autical

-0.64

rontal

-0.63

pecting

-0.63

 Occup

-0.63

POSITIVE LOGITS

Mail

0.69

ELF

0.68

elvet

0.68

Edge

0.67

ullivan

0.64

ICE

0.63

 Sakura

0.62

ãĤ®

0.61

hops

0.59

 rele

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.