INDEX

Explanations

mentions of the word "odor" with varying degrees of emphasis or relevance

oai_token-act-pair · gpt-3.5-turbo

references to odors

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

cedented

-0.65

peak

-0.63

Canada

-0.62

 Peaks

-0.62

 pasture

-0.60

 WARN

-0.59

 selected

-0.59

FT

-0.58

UGE

-0.58

 bargaining

-0.58

POSITIVE LOGITS

odor

1.27

owsky

1.07

ovic

0.92

inator

0.90

osity

0.90

DragonMagazine

0.90

ovich

0.89

oslav

0.84

nance

0.83

loo

0.82

Activations Density 0.008%

mentions of the word "odor" with varying degrees of emphasis or relevance

references to odors

No Known Activations