INDEX

Explanations

instances of the word "instill" and its variations

oai_token-act-pair · gpt-3.5-turbo

forms of the word "install" and related terms implying installation or introduction

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

neau

-0.82

udeau

-0.79

ixel

-0.74

opoulos

-0.71

icro

-0.67

Kro

-0.66

ouch

-0.63

iddled

-0.63

 athlet

-0.62

ibble

-0.62

POSITIVE LOGITS

 anew

0.80

 hatred

0.74

spir

0.70

Ire

0.66

 memories

0.64

BALL

0.64

 humility

0.64

FORMATION

0.63

 havoc

0.62

 Divinity

0.62

Activations Density 0.110%

instances of the word "instill" and its variations

forms of the word "install" and related terms implying installation or introduction

No Comments

No Known Activations