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

Jr

-0.68

 opio

-0.68

 condom

-0.66

 subscrib

-0.66

utical

-0.64

orescence

-0.64

 retaliate

-0.64

)))

-0.63

phe

-0.62

 targ

-0.62

POSITIVE LOGITS

tnc

0.80

chin

0.67

ulnerable

0.64

 occupations

0.64

laugh

0.63

 Norn

0.63

yan

0.63

bara

0.62

ilan

0.62

alus

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.