INDEX

Explanations

keywords related to hints or threshold concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Spitze

-0.48

싶

-0.48

queles

-0.47

 lectores

-0.45

 başına

-0.44

 remand

-0.44

 laude

-0.43

 muñecas

-0.43

 recours

-0.42

 nominate

-0.42

POSITIVE LOGITS

0.63

 GenerationType

0.59

Ay

0.57

Ay

0.52

//

0.48

 findViewById

0.48

 مشين

0.48

Frame

0.47

OGND

0.47

PhysRev

0.46

Activations Density 0.304%

keywords related to hints or threshold concepts

No Comments

No Known Activations