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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ã©s

-0.71

lement

-0.66

lest

-0.64

atro

-0.63

tag

-0.63

ansson

-0.62

enge

-0.62

lection

-0.61

Ã

-0.60

hers

-0.60

POSITIVE LOGITS

pload

0.76

 Bucc

0.69

quickShipAvailable

0.67

isSpecialOrderable

0.65

Brother

0.64

ONSORED

0.64

 Founders

0.63

kell

0.63

 calves

0.62

fram

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.