INDEX

Explanations

passive voice constructions and phrases indicating conditions or predictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 snippetHide

-0.67

RenderAtEndOf

-0.61

::::::::

-0.58

 مشين

-0.53

 carre

-0.52

 ***!

-0.51

ete

-0.50

ArgumentParser

-0.48

المكان

-0.47

onViewCreated

-0.47

POSITIVE LOGITS

]--;

0.69

copyWith

0.61

<?>>

0.60

msford

0.60

ódó

0.59

SBATCH

0.57

lepiej

0.57

bbene

0.57

łyż

0.56

└──

0.55

Activations Density 1.542%

passive voice constructions and phrases indicating conditions or predictions

No Comments

No Known Activations