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

 faults

-0.67

 Canary

-0.66

orter

-0.64

 chall

-0.64

 offline

-0.63

 Constantin

-0.63

 backups

-0.62

bis

-0.61

']

-0.60

 Peak

-0.60

POSITIVE LOGITS

ghan

0.77

erenn

0.76

kiss

0.72

lihood

0.72

imaru

0.70

ISON

0.70

Pwr

0.70

>>\

0.70

gey

0.70

gh

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.