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

achu

-0.67

arius

-0.65

mson

-0.64

 PACs

-0.63

edom

-0.63

é¾

-0.62

ngth

-0.62

 Amon

-0.62

orthern

-0.61

liga

-0.61

POSITIVE LOGITS

 appell

0.82

æĪ¦

0.70

 Lieberman

0.67

eps

0.66

 inmates

0.64

IAN

0.64

ISA

0.63

Dial

0.63

Todd

0.63

IAS

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.