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

oter

-0.77

urrent

-0.69

 Merchant

-0.66

uctor

-0.65

 newsp

-0.65

achus

-0.64

 unnecess

-0.62

 TAMADRA

-0.62

 tremend

-0.60

orers

-0.60

POSITIVE LOGITS

pak

0.67

dp

0.66

dash

0.63

pes

0.62

adal

0.61

wark

0.60

dimension

0.60

 Yorkshire

0.59

cms

0.59

imb

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.