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

Loading

-0.82

MU

-0.79

EEK

-0.79

REE

-0.74

NRS

-0.73

çĦ

-0.70

atari

-0.69

IRO

-0.69

Î»

-0.68

tip

-0.66

POSITIVE LOGITS

CTR

0.80

 topical

0.66

 Commando

0.65

uchs

0.63

 Wein

0.63

pmwiki

0.63

 urgent

0.61

 Dull

0.61

 foremost

0.60

 concentrating

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.