INDEX

Explanations

instances where the text expresses a lack of concern or indifference

oai_token-act-pair · gpt-3.5-turbo

expressions of indifference or lack of concern

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

igslist

-0.85

BuyableInstoreAndOnline

-0.84

uthor

-0.81

pload

-0.79

auri

-0.79

-0.77

etheus

-0.75

DragonMagazine

-0.73

ompl

-0.70

ieve

-0.70

POSITIVE LOGITS

ogie

0.76

lessly

0.70

 quality

0.66

 upkeep

0.66

noon

0.65

 cents

0.64

sec

0.64

tone

0.64

 dearly

0.63

 anymore

0.62

Activations Density 0.142%

instances where the text expresses a lack of concern or indifference

expressions of indifference or lack of concern

No Comments

No Known Activations