INDEX

Explanations

features or components of products which are adjustable or interchangeable

oai_token-act-pair · gpt-3.5-turbo

terms related to adjustable or interchangeable features in products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

emi

-0.89

abal

-0.79

swick

-0.78

elf

-0.76

externalActionCode

-0.76

ym

-0.74

udic

-0.74

iquette

-0.74

eln

-0.73

src

-0.73

POSITIVE LOGITS

 modular

1.10

 removable

0.98

 storage

0.92

 housing

0.89

 accessory

0.88

 adjustable

0.84

 platforms

0.83

 seating

0.83

 auxiliary

0.83

 carriage

0.82

Activations Density 0.071%

features or components of products which are adjustable or interchangeable

terms related to adjustable or interchangeable features in products

No Comments

No Known Activations