INDEX

Explanations

references to loss or losing experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

OGND

-0.97

 complémentaires

-0.93

PhysRev

-0.79

 referenties

-0.77

httphttps

-0.75

Datuak

-0.75

theless

-0.75

 שהוא

-0.73

+#+

-0.71

propTypes

-0.70

POSITIVE LOGITS

 loss

1.48

 Loss

1.41

 lost

1.40

Lose

1.38

 LOSS

1.33

 Lose

1.32

Loss

1.31

 LOST

1.31

loss

1.29

lost

1.28

Activations Density 0.065%

references to loss or losing experiences

No Comments

No Known Activations