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

ruciating

-0.79

ĨĴ

-0.77

EStreamFrame

-0.76

acly

-0.76

abulary

-0.70

chie

-0.69

inction

-0.68

hell

-0.67

ugu

-0.66

ciating

-0.64

POSITIVE LOGITS

IRD

0.73

 Isles

0.67

ORGE

0.67

yip

0.65

 behold

0.63

 IMAGES

0.63

 railways

0.63

ESA

0.62

 wires

0.60

sb

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.