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

amba

-0.72

avez

-0.70

ilib

-0.69

 encour

-0.68

aru

-0.67

bleacher

-0.67

adeon

-0.64

 spoil

-0.62

externalActionCode

-0.61

alloc

-0.60

POSITIVE LOGITS

special

0.69

 Zurich

0.68

found

0.64

Pal

0.64

 Hilbert

0.64

 Perse

0.63

Links

0.63

Pan

0.63

tel

0.63

held

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.