INDEX

Explanations

names of people

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to individuals, particularly in a sports context

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

 mathemat

-0.61

cyt

-0.61

 defic

-0.61

 horizont

-0.60

Ü

-0.59

 polar

-0.58

ccording

-0.58

abouts

-0.56

 irregularities

-0.56

âĵĺ

-0.56

POSITIVE LOGITS

Jr

1.31

heimer

1.08

baugh

1.01

Sr

0.98

kamp

0.94

Jr

0.94

meier

0.90

hoff

0.89

wine

0.88

velt

0.88

Activations Density 0.217%

names of people

proper nouns related to individuals, particularly in a sports context

No Comments

No Known Activations