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

ercise

-0.78

uin

-0.73

reth

-0.67

regate

-0.67

orph

-0.65

way

-0.64

oen

-0.64

tein

-0.64

ateg

-0.63

otation

-0.62

POSITIVE LOGITS

srf

0.86

 tradem

0.86

rons

0.73

 Pixie

0.70

 gobl

0.68

 pestic

0.67

 stellar

0.66

Ń·

0.66

 Fahrenheit

0.66

 Debor

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.