INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

cffffcc

-0.70

atown

-0.70

toggle

-0.67

apego

-0.67

 glean

-0.65

hement

-0.63

acements

-0.63

 cheered

-0.63

 trillions

-0.62

bg

-0.61

POSITIVE LOGITS

annot

0.70

atta

0.69

 qualifying

0.66

ucha

0.66

Ver

0.66

oxide

0.66

 Serbian

0.65

 coli

0.64

Cas

0.64

mic

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.