INDEX

Explanations

nutritional information such as ingredients, vitamins, and minerals in a structured format

oai_token-act-pair · gpt-3.5-turbo

references to favorite items or ratings associated with them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

=$

-0.75

Wallet

-0.71

prototype

-0.66

 smugglers

-0.64

staking

-0.63

 slic

-0.63

omics

-0.62

PDF

-0.60

soDeliveryDate

-0.59

STD

-0.59

POSITIVE LOGITS

ã

0.79

[+

0.78

ãħĭ

0.76

/-

0.73

BuyableInstoreAndOnline

0.71

 Jenn

0.71

irez

0.66

 Respect

0.66

 Sapp

0.66

 Annie

0.65

Activations Density 0.010%

nutritional information such as ingredients, vitamins, and minerals in a structured format

references to favorite items or ratings associated with them

No Comments

No Known Activations