INDEX

Explanations

words related to design or intention

oai_token-act-pair · gpt-3.5-turbo

phrases indicating design intent or purpose

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SPONSORED

-0.88

achus

-0.84

 TAMADRA

-0.77

natureconservancy

-0.76

vous

-0.66

NCT

-0.66

Â§

-0.62

jac

-0.61

cise

-0.61

 consequ

-0.60

POSITIVE LOGITS

ueller

0.78

DEBUG

0.73

ertodd

0.68

 satir

0.65

 Gund

0.64

 shielding

0.64

 Salvador

0.64

 certific

0.63

 Dahl

0.61

 Boeing

0.60

Activations Density 0.222%

words related to design or intention

phrases indicating design intent or purpose

No Comments

No Known Activations