INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Fernand

-0.89

spir

-0.79

 turb

-0.70

 destro

-0.67

 Juno

-0.66

 iceberg

-0.66

 Haitian

-0.66

 scal

-0.65

BuyableInstoreAndOnline

-0.65

 mortg

-0.64

POSITIVE LOGITS

iden

0.74

abad

0.74

ornia

0.73

obi

0.72

conservancy

0.69

atible

0.68

istries

0.64

ederal

0.64

ebus

0.63

Insert

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.