INDEX

Explanations

references to sports leagues, particularly the Premier League

oai_token-act-pair · gpt-3.5-turbo

references to the Premier League and its associated teams or events

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

Premier League, La Liga, Serie A, FA Cup, Bundesliga, or Championship

Explanation Uploaded by User

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

romy

-0.94

Bey

-0.83

UW

-0.83

TED

-0.82

ERSON

-0.82

 Navajo

-0.80

behavior

-0.79

enegger

-0.78

eor

-0.76

Larry

-0.76

POSITIVE LOGITS

 strugg

1.17

 footballer

1.13

 defences

1.01

 rivals

0.97

 relegation

0.97

 League

0.94

 organising

0.90

 organisation

0.90

 league

0.90

 unbeaten

0.88

Activations Density 0.102%

references to sports leagues, particularly the Premier League

references to the Premier League and its associated teams or events

Premier League, La Liga, Serie A, FA Cup, Bundesliga, or Championship

No Comments

No Known Activations