INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 snail

-0.71

forcement

-0.70

itual

-0.69

pport

-0.68

picture

-0.67

iqueness

-0.67

hetical

-0.67

 attachment

-0.66

ilee

-0.66

ription

-0.64

POSITIVE LOGITS

 Bullets

0.82

 Breat

0.73

 turns

0.67

 Flavoring

0.66

 Rend

0.64

 ACPI

0.64

 Dise

0.62

 Realms

0.62

bol

0.62

 Bundy

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.