INDEX

Explanations

terms related to invalidity or null values in a technical or legal context

oai_token-act-pair · gpt-3.5-turbo

terms related to nullification or cancellation in various contexts

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

Downloadha

-0.80

 millenn

-0.78

 livest

-0.76

 exha

-0.76

DonaldTrump

-0.74

BOOK

-0.73

 hemor

-0.69

 toget

-0.69

ilitating

-0.68

 ingred

-0.67

POSITIVE LOGITS

ifying

1.27

ptr

1.23

ifies

1.18

ified

1.16

ification

1.09

ifier

1.04

ify

1.00

ifiers

0.97

ities

0.94

eenth

0.91

Activations Density 0.023%

terms related to invalidity or null values in a technical or legal context

terms related to nullification or cancellation in various contexts

No Comments

No Known Activations