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

merce

-0.75

puter

-0.72

ggles

-0.72

ndra

-0.70

atel

-0.69

enery

-0.68

=>

-0.68

okÃ©

-0.67

ighty

-0.67

rencies

-0.67

POSITIVE LOGITS

 brand

0.71

CHA

0.66

 Welsh

0.63

 fuck

0.61

 relaxed

0.61

 mutated

0.60

Charl

0.58

 Shot

0.58

 Hung

0.58

Champ

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.