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

ffect

-0.72

 Strait

-0.70

 Patch

-0.70

Spot

-0.62

 Pigs

-0.61

 Directory

-0.61

functional

-0.60

gnu

-0.59

 section

-0.58

alf

-0.57

POSITIVE LOGITS

²¾

0.83

 thous

0.77

awa

0.74

ryu

0.73

ritch

0.73

 Skydragon

0.69

amaz

0.67

Ħ¢

0.67

kaya

0.67

 testify

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.