INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ascript

-0.80

agine

-0.79

emetery

-0.71

afia

-0.67

inarily

-0.65

 timet

-0.63

 unden

-0.63

ts

-0.63

 Typh

-0.60

 strongest

-0.60

POSITIVE LOGITS

ering

0.68

 Mellon

0.66

0.65

olor

0.64

nav

0.63

Timeout

0.62

erness

0.62

bra

0.62

Topic

0.62

ESSION

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.