INDEX

Explanations

occurrences of the word "more" signaling a comparative context

oai_token-act-pair · gpt-3.5-turbo

instances of the word "more"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

atan

-0.81

uca

-0.73

xtap

-0.68

uckle

-0.68

adium

-0.64

idated

-0.62

pton

-0.61

imaru

-0.61

abama

-0.60

ipment

-0.60

POSITIVE LOGITS

 importantly

1.63

 than

1.21

ado

0.93

 millenn

0.89

 Than

0.86

 interestingly

0.84

 accurately

0.81

 controvers

0.79

 broadly

0.78

 stringent

0.78

Activations Density 0.122%

occurrences of the word "more" signaling a comparative context

instances of the word "more"

No Comments

No Known Activations