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

meet

-0.68

eye

-0.63

mental

-0.63

 toile

-0.61

resy

-0.61

BY

-0.60

 Measures

-0.60

 conditioning

-0.60

 Incident

-0.59

lihood

-0.59

POSITIVE LOGITS

ocene

0.75

ulhu

0.72

enium

0.70

osion

0.70

ulz

0.69

agonist

0.69

vae

0.69

anguage

0.68

osaurs

0.67

uments

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.