INDEX

Explanations

mentions of the term "Pirate" and related entities, like Pirate Bay and Pirate Party

oai_token-act-pair · gpt-3.5-turbo

references to "The Pirate Bay" and related terms

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

uggest

-0.90

enegger

-0.81

earchers

-0.74

cue

-0.74

olving

-0.73

ithing

-0.73

uating

-0.71

upon

-0.70

mble

-0.69

perse

-0.69

POSITIVE LOGITS

Pir

0.89

 Penguin

0.87

 Pirate

0.87

 Warrior

0.84

 Party

0.79

 Parties

0.79

Browser

0.71

 Islands

0.71

lean

0.71

 Caucus

0.70

Activations Density 0.015%

mentions of the term "Pirate" and related entities, like Pirate Bay and Pirate Party

references to "The Pirate Bay" and related terms

No Comments

No Known Activations