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

Developer

-0.99

anium

-0.77

inement

-0.74

Reviewer

-0.74

thumbnails

-0.72

vals

-0.71

 digs

-0.70

Numbers

-0.69

zx

-0.68

apses

-0.68

POSITIVE LOGITS

 Fisheries

0.70

nce

0.69

 Hurricane

0.64

Lok

0.64

gey

0.62

 Prosper

0.62

 Glover

0.62

 Bulgar

0.61

 Corsair

0.61

 bounty

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.