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

opian

-0.74

stress

-0.70

nown

-0.67

 constitu

-0.67

antine

-0.65

 Tanz

-0.65

perm

-0.64

apult

-0.64

ournal

-0.64

 relaxed

-0.63

POSITIVE LOGITS

Merit

0.71

 fault

0.68

Reviewer

0.68

 Transactions

0.67

 mosques

0.66

Publisher

0.65

 reactors

0.65

Reporting

0.64

Unit

0.64

 faults

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.