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

\\\\\\\\

-0.80

 watered

-0.74

Lago

-0.71

ertodd

-0.70

Runner

-0.69

////////////////////////////////

-0.68

require

-0.67

 Centauri

-0.63

riber

-0.63

yond

-0.63

POSITIVE LOGITS

icho

0.73

imil

0.67

inois

0.67

ules

0.66

emb

0.61

Cav

0.58

 isol

0.58

phony

0.58

ired

0.57

âĢİ

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.