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

icans

-0.79

isson

-0.77

 Franco

-0.75

ihil

-0.71

ican

-0.70

inelli

-0.68

ques

-0.68

 divers

-0.67

olls

-0.67

soever

-0.67

POSITIVE LOGITS

¥µ

0.75

¿½

0.73

 intrusion

0.71

 Highlights

0.71

ļé

0.70

LG

0.68

 regression

0.68

 flaw

0.66

 slideshow

0.66

hib

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.