INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

IB

-0.69

ISTER

-0.68

 Gate

-0.68

uders

-0.66

osuke

-0.65

 intangible

-0.64

 Omar

-0.63

uten

-0.60

 obedient

-0.60

 unhappy

-0.60

POSITIVE LOGITS

aunder

0.75

payer

0.69

 Thrones

0.66

ichick

0.65

olated

0.65

ly

0.65

lav

0.64

keeping

0.63

 lett

0.62

meg

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.