INDEX

Explanations

terms related to enhancement or improvement

oai_token-act-pair · gpt-3.5-turbo

terms associated with enhancement, particularly in various contexts such as medical, technological, or social improvements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soDeliveryDate

-0.81

-0.78

hare

-0.74

behind

-0.70

place

-0.63

metal

-0.63

shr

-0.62

DIR

-0.61

wic

-0.60

ben

-0.60

POSITIVE LOGITS

ments

1.24

mentation

0.98

 senses

0.92

mble

0.85

 capacities

0.85

anced

0.80

iveness

0.80

ment

0.79

 enhances

0.78

ement

0.78

Activations Density 0.088%

terms related to enhancement or improvement

terms associated with enhancement, particularly in various contexts such as medical, technological, or social improvements

No Comments

No Known Activations