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

essa

-0.94

ppard

-0.86

hart

-0.85

pillar

-0.83

nex

-0.82

zens

-0.82

heed

-0.81

haven

-0.81

orio

-0.81

oak

-0.78

POSITIVE LOGITS

 Purg

0.75

NZ

0.71

 Phar

0.67

 Cerberus

0.66

 Psychic

0.66

BN

0.64

 Panic

0.63

 slang

0.62

 Conversion

0.61

 Palin

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.