INDEX

Explanations

the word "no" followed by a word or phrase that signifies absence or limitation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "no" indicating absence or lack of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atech

-0.77

DragonMagazine

-0.77

lish

-0.76

ocard

-0.75

thouse

-0.74

lass

-0.73

merce

-0.72

andise

-0.72

aly

-0.70

rue

-0.69

POSITIVE LOGITS

 regard

0.92

 interruption

0.88

 intention

0.83

 expectation

0.78

 measurable

0.78

 accompanying

0.78

 exception

0.75

 conceivable

0.74

 predetermined

0.74

 exceptions

0.74

Activations Density 0.098%

the word "no" followed by a word or phrase that signifies absence or limitation

instances of the word "no" indicating absence or lack of something

No Comments

No Known Activations