INDEX

Explanations

descriptions of physical positions and body placements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 cref

-0.56

LEncoder

-0.55

zib

-0.53

 NUKAT

-0.52

 المعيارى

-0.52

 Administrativna

-0.52

 JSTOR

-0.52

Zobacz

-0.51

Lähteet

-0.50

 actionPerformed

-0.49

POSITIVE LOGITS

 kneeling

0.94

 kneel

0.92

 knees

0.85

 knelt

0.71

 prostrate

0.71

 knee

0.68

Kne

0.67

Lying

0.67

 Lying

0.63

 genoux

0.61

Activations Density 0.156%

descriptions of physical positions and body placements

No Comments

No Known Activations