INDEX

Explanations

words related to disqualification, ineligibility, and forfeiture

oai_token-act-pair · gpt-3.5-turbo

terms related to disqualification and ineligibility

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Lans

-0.78

 Spice

-0.71

ttp

-0.71

OTOS

-0.68

elf

-0.65

Esp

-0.64

 Merc

-0.63

 Mass

-0.62

TPP

-0.62

ulton

-0.61

POSITIVE LOGITS

 disqual

1.48

 disqualified

1.24

ifying

1.01

ifications

1.00

ifies

0.99

ifiers

0.93

ification

0.89

ify

0.87

ifier

0.86

mma

0.81

Activations Density 0.013%

words related to disqualification, ineligibility, and forfeiture

terms related to disqualification and ineligibility

No Known Activations