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

IDA

-0.77

ãĥĻ

-0.74

 Volunte

-0.73

ãĥĩãĤ£

-0.67

 Farming

-0.65

 elector

-0.64

 VIDEOS

-0.63

 Berks

-0.62

[+

-0.61

IRC

-0.61

POSITIVE LOGITS

places

0.79

stein

0.76

ogn

0.75

idas

0.73

jack

0.69

arson

0.69

work

0.68

matter

0.68

illac

0.68

bending

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.