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

netflix

-0.76

ãĥª

-0.69

appointed

-0.68

asking

-0.66

 Wast

-0.64

 respectively

-0.62

Ud

-0.60

NESS

-0.59

 Username

-0.58

phia

-0.57

POSITIVE LOGITS

osterone

0.75

 Koran

0.66

 sights

0.66

 vantage

0.64

rogram

0.64

 Quran

0.64

 Cambod

0.63

=-=-=-=-=-=-=-=-

0.63

oeuv

0.63

 Parish

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.