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

 govern

-0.83

 à¨

-0.77

oliberal

-0.72

 governors

-0.69

wig

-0.66

ews

-0.66

 mascul

-0.65

×

-0.65

ahime

-0.65

 groom

-0.64

POSITIVE LOGITS

Bet

0.83

 Suns

0.76

 Stanton

0.74

 Starr

0.72

Coll

0.71

 Playoff

0.70

 Mara

0.69

Rep

0.67

 Stard

0.66

Ann

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.