INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

etheless

-0.82

 whiff

-0.74

pite

-0.71

 sensing

-0.70

urdue

-0.68

 Notting

-0.64

 cogn

-0.63

JPM

-0.63

wart

-0.63

 realizing

-0.63

POSITIVE LOGITS

kat

0.70

eson

0.70

Afee

0.69

VERTISEMENT

0.68

ENG

0.68

---------

0.67

çī

0.67

rones

0.67

ð

0.67

Gear

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.