INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Conversation

-0.73

 physicist

-0.65

 scientist

-0.60

 posit

-0.59

aughter

-0.58

 sentence

-0.58

 dismantled

-0.58

 synthes

-0.57

 Goodbye

-0.57

 Matter

-0.56

POSITIVE LOGITS

yip

0.86

lite

0.83

aminer

0.82

DragonMagazine

0.79

psey

0.79

ournal

0.75

ullivan

0.73

0.72

rates

0.71

imaru

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.