INDEX

Explanations

specific programming or mathematical terminology related to matrices and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 utafitiHapana

-0.59

IntoConstraints

-0.42

德

-0.41

 autorytatywna

-0.40

 gynhyrchwyd

-0.40

 Chwiliwch

-0.39

 insuffisamment

-0.39

 Signalez

-0.38

Dat

-0.38

 Door

-0.36

POSITIVE LOGITS

 диа

1.76

dia

1.71

 dial

1.60

 діа

1.55

 Dial

1.55

Dia

1.52

 Diane

1.50

 Диа

1.48

di

1.47

 Diana

1.47

Activations Density 0.669%

specific programming or mathematical terminology related to matrices and data structures

No Comments

No Known Activations