INDEX

Explanations

phrases or acronyms related to the term "NS"

oai_token-act-pair · gpt-3.5-turbo

mentions of "NS" followed by numbers or abbreviations, likely indicating regulatory organizations or technical terminology

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

fare

-0.80

ously

-0.79

icago

-0.69

aday

-0.67

iences

-0.66

âĸ¬âĸ¬

-0.65

gered

-0.65

wards

-0.64

ozyg

-0.63

wig

-0.63

POSITIVE LOGITS

FW

1.42

HT

0.88

UT

0.86

fw

0.85

ESSION

0.84

ettings

0.81

ERC

0.80

ypes

0.80

IRO

0.80

erv

0.80

Activations Density 0.017%

phrases or acronyms related to the term "NS"

mentions of "NS" followed by numbers or abbreviations, likely indicating regulatory organizations or technical terminology

No Comments

No Known Activations