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

cffffcc

-0.81

 "$:/

-0.80

 poisoning

-0.68

IPM

-0.66

-0.63

steamapps

-0.62

 disqual

-0.61

uana

-0.61

EStream

-0.61

 hypers

-0.60

POSITIVE LOGITS

onsense

0.80

atron

0.68

iqueness

0.66

 Lyons

0.65

*****

0.63

 Thib

0.62

atures

0.62

 Scha

0.61

utter

0.61

ager

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.