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

uate

-0.67

 Wenger

-0.67

 vigilante

-0.65

authent

-0.64

ĸļ

-0.64

uating

-0.63

eve

-0.63

 senses

-0.62

geist

-0.62

 opio

-0.61

POSITIVE LOGITS

ainment

0.82

imated

0.75

istance

0.72

Children

0.69

utch

0.66

rition

0.66

otos

0.66

ission

0.64

olls

0.63

BM

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.