INDEX

Explanations

numbers and codes

oai_token-act-pair · gpt-3.5-turbo

instances of numerical data or statistics related to events or circumstances

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 eleph

-0.88

 neighbouring

-0.85

 spir

-0.81

 shelling

-0.79

ortunately

-0.78

 neighboring

-0.78

 resulting

-0.77

 regener

-0.75

 citiz

-0.74

 servic

-0.74

POSITIVE LOGITS

First

1.63

1.62

Firstly

1.62

Introduction

1.56

Myth

1.49

PART

1.47

FIR

1.47

Continue

1.47

Overview

1.47

THE

1.46

Activations Density 0.276%

numbers and codes

instances of numerical data or statistics related to events or circumstances

No Comments

No Known Activations