INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Detention

-0.66

CLASSIFIED

-0.66

uer

-0.64

 administr

-0.64

 compe

-0.64

hered

-0.64

 bonded

-0.63

zee

-0.61

 hiber

-0.59

 ambassador

-0.59

POSITIVE LOGITS

omen

0.83

ynski

0.71

geon

0.67

emen

0.67

obl

0.66

ASE

0.65

yrinth

0.65

acons

0.65

opathic

0.64

asing

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.