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

ovych

-0.79

 orally

-0.69

weeney

-0.64

rams

-0.62

 Canaver

-0.61

Cyr

-0.61

 plutonium

-0.60

 Memor

-0.59

brance

-0.59

 Lester

-0.58

POSITIVE LOGITS

âĵĺ

0.70

nces

0.68

shapeshifter

0.66

Fair

0.66

ounced

0.65

BILITIES

0.65

uper

0.65

soType

0.63

Spawn

0.62

joined

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.