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

ļéĨĴ

-0.94

©¶æ¥µ

-0.84

Ĥª

-0.80

ãĥĥãĥī

-0.79

LEASE

-0.78

ãĤ¦ãĤ¹

-0.78

Marginal

-0.71

BIP

-0.69

ODY

-0.69

wcs

-0.69

POSITIVE LOGITS

indal

0.67

thur

0.62

 Batt

0.61

handed

0.61

 cartridges

0.61

hur

0.60

ounced

0.60

 condoms

0.60

 brist

0.59

reb

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.