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

agra

-0.93

 implants

-0.64

 title

-0.64

 fixtures

-0.62

 titles

-0.62

Tickets

-0.62

 Bers

-0.61

 Tsukuyomi

-0.60

}"

-0.59

 catchy

-0.59

POSITIVE LOGITS

ility

0.83

itud

0.81

jri

0.77

oult

0.74

afety

0.74

onder

0.73

ierre

0.68

conduct

0.68

udeau

0.67

ourning

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.