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

 Yelp

-0.68

 Jury

-0.67

 Kung

-0.65

 certific

-0.64

 calculation

-0.62

 Shooter

-0.61

 Realms

-0.61

 shareholder

-0.59

ework

-0.59

 ILCS

-0.59

POSITIVE LOGITS

rand

0.76

etsk

0.71

dates

0.65

way

0.65

":"/

0.64

ras

0.62

rament

0.61

enta

0.60

terday

0.60

WH

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.