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

 hijab

-0.76

 unlaw

-0.70

ay

-0.68

fal

-0.67

ItemTracker

-0.65

urred

-0.64

*/(

-0.63

ural

-0.62

romy

-0.62

ummer

-0.61

POSITIVE LOGITS

 earnest

0.69

ÃĥÃĤ

0.68

Serv

0.65

ymes

0.65

anwhile

0.64

ß

0.63

 Bastard

0.62

éŃĶ

0.60

 salvage

0.60

Ò

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.