INDEX

Explanations

phrases related to vehicles and accidents

oai_token-act-pair · gpt-3.5-turbo

references to various types of vehicles involved in incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cffff

-0.71

DragonMagazine

-0.70

utical

-0.69

maxwell

-0.67

figure

-0.67

 Flavoring

-0.65

 Medals

-0.65

 Seym

-0.64

 mornings

-0.64

reality

-0.64

POSITIVE LOGITS

 parked

1.08

 belonging

0.93

 driver

0.91

 loaded

0.89

wagon

0.88

 crashed

0.87

load

0.87

SUV

0.86

 transporting

0.86

 trunk

0.84

Activations Density 0.111%

phrases related to vehicles and accidents

references to various types of vehicles involved in incidents

No Comments

No Known Activations