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

ALLY

-0.82

 incidentally

-0.66

 Nare

-0.63

nee

-0.63

ASE

-0.63

*)

-0.63

 tragically

-0.62

KR

-0.61

KE

-0.60

IDES

-0.60

POSITIVE LOGITS

emate

0.73

ility

0.72

ware

0.70

algia

0.70

emonic

0.69

thing

0.68

 Dupl

0.68

estyles

0.68

 Gord

0.67

enza

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.