INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ategory

-0.69

cellence

-0.66

itaire

-0.65

anyl

-0.63

 funnel

-0.62

inventoryQuantity

-0.62

 Created

-0.62

 sacrific

-0.61

inyl

-0.60

iltr

-0.60

POSITIVE LOGITS

asar

0.74

HEAD

0.65

×©

0.63

 Meridian

0.63

 Mercedes

0.61

Dash

0.61

 Rally

0.61

 Lans

0.61

Scotland

0.60

 Emin

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.