INDEX

Explanations

things related to legal and investigative procedures, such as registering FIRs

oai_token-act-pair · gpt-3.5-turbo

instances of time-related references in events or narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 destro

-0.63

senal

-0.58

 advoc

-0.57

 eleph

-0.56

acebook

-0.55

 nodd

-0.53

 outwe

-0.52

emale

-0.52

 corrid

-0.52

akespe

-0.52

POSITIVE LOGITS

 Shutdown

0.46

HOU

0.44

 Background

0.43

!--

0.42

flush

0.42

BLIC

0.41

 Marvel

0.40

catentry

0.40

 Introduction

0.40

 Judicial

0.40

Activations Density 1.242%

things related to legal and investigative procedures, such as registering FIRs

instances of time-related references in events or narratives

No Comments

No Known Activations