INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Centauri

-0.77

 Bezos

-0.73

 Guys

-0.71

 Seat

-0.68

 pulp

-0.68

 Kafka

-0.67

arrass

-0.67

 McCarthy

-0.64

urga

-0.64

 Tsuk

-0.64

POSITIVE LOGITS

uter

0.80

accompan

0.72

joining

0.71

helps

0.69

\<

0.69

nyder

0.69

yout

0.67

ctrl

0.66

sylv

0.66

cu

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.