INDEX

Explanations

words related to the name "Martha"

oai_token-act-pair · gpt-3.5-turbo

variations of the word "ha" that likely indicate laughter or amusement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

atories

-0.79

tailed

-0.71

acity

-0.67

rats

-0.66

 outgoing

-0.65

night

-0.64

bats

-0.64

brain

-0.63

ocity

-0.63

ãĤ±

-0.63

POSITIVE LOGITS

wn

1.19

user

1.08

illard

1.03

irst

0.91

emi

0.89

arma

0.87

 Pradesh

0.86

ancock

0.86

azard

0.86

enei

0.82

Activations Density 0.044%

words related to the name "Martha"

variations of the word "ha" that likely indicate laughter or amusement

No Comments

No Known Activations