INDEX

Explanations

cautions and warnings related to health and medication usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 виправивши

-0.71

følgelig

-0.69

الإنجليزية

-0.60

HideFlags

-0.60

anggil

-0.59

 manageable

-0.58

 fairest

-0.58

帖最后由

-0.57

lysm

-0.57

ArgumentParser

-0.56

POSITIVE LOGITS

 excessively

0.87

 слишком

0.87

 terlalu

0.87

too

0.82

 unsupervised

0.80

 troppo

0.79

 excessive

0.79

 overly

0.79

 demasi

0.78

too

0.77

Activations Density 0.447%

cautions and warnings related to health and medication usage

No Comments

No Known Activations