INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

paio

-0.76

obar

-0.74

ador

-0.72

arch

-0.71

ubb

-0.70

ospace

-0.70

ographics

-0.68

zag

-0.67

itar

-0.67

 Gutenberg

-0.66

POSITIVE LOGITS

 Canad

0.78

 cough

0.67

 Scythe

0.65

 cocktail

0.63

 Bellev

0.63

aka

0.62

 Cock

0.61

 NOTE

0.61

 Creed

0.61

 laugh

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.