INDEX

Explanations

abbreviations or acronyms containing "NS"

oai_token-act-pair · gpt-3.5-turbo

the acronym "NS" and its variants related to various contexts in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ra

-0.63

irgin

-0.60

 doub

-0.59

 failing

-0.57

 Mile

-0.57

 techno

-0.57

 tidy

-0.57

 Horse

-0.56

 caution

-0.56

 empty

-0.56

POSITIVE LOGITS

FW

1.23

NS

1.22

fw

1.07

ertodd

1.04

ESSION

0.91

erves

0.91

HT

0.90

ettings

0.88

erve

0.88

emonic

0.83

Activations Density 0.004%

abbreviations or acronyms containing "NS"

the acronym "NS" and its variants related to various contexts in the document

No Comments

No Known Activations