INDEX

Explanations

names of Formula One drivers and teams

oai_token-act-pair · gpt-3.5-turbo

references to Formula One racing and its participants

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

Newsletter

-0.90

taboola

-0.85

DragonMagazine

-0.84

tumblr

-0.79

PROV

-0.79

Sexual

-0.79

ulhu

-0.78

 Neighbor

-0.78

 Barron

-0.78

Washington

-0.78

POSITIVE LOGITS

 tyre

1.17

 racing

1.17

 braking

1.09

 Racing

1.05

 racer

1.05

 tyres

1.05

 doping

1.03

 chassis

0.96

 lapt

0.95

 championship

0.92

Activations Density 0.153%

names of Formula One drivers and teams

references to Formula One racing and its participants

No Comments

No Known Activations