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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abouts

-0.72

IRC

-0.72

################

-0.67

Pers

-0.66

Torrent

-0.66

Pis

-0.63

Brow

-0.62

 Anarch

-0.61

 comrade

-0.61

\":

-0.60

POSITIVE LOGITS

mble

0.72

ļéĨĴ

0.70

¥µ

0.69

azard

0.68

 sqor

0.67

itzer

0.66

aughtered

0.65

 airborne

0.64

pecially

0.62

endi

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.