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

Deal

-0.66

 Kafka

-0.66

Dialogue

-0.64

DT

-0.64

 comedians

-0.64

 Gorsuch

-0.63

Ada

-0.61

 Voting

-0.61

 Pengu

-0.61

Stack

-0.60

POSITIVE LOGITS

hov

0.89

 ancestral

0.74

 carn

0.69

fle

0.68

sic

0.68

arent

0.67

ciplinary

0.65

»Ĵ

0.65

icum

0.64

 watering

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.