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

Mae

-0.65

morrow

-0.63

AMI

-0.63

 Okinawa

-0.59

|--

-0.58

CHAPTER

-0.57

 endings

-0.56

 Mara

-0.56

 repetition

-0.56

 complement

-0.55

POSITIVE LOGITS

ebus

0.90

ãĥ¼ãĤ¯

0.82

bler

0.72

atos

0.72

 Passive

0.72

chnology

0.70

iannopoulos

0.69

bern

0.68

overe

0.67

rahim

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.