INDEX

Explanations

references to historical conflicts and treaties involving national powers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/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.21.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

 superpowers

-0.90

 visuals

-0.89

 backstory

-0.86



-0.86

iffance

-0.84

 nuanced

-0.84

 comedic

-0.82

IBLIO

-0.81

 blurry

-0.81

 accolades

-0.81

POSITIVE LOGITS

 objectForKey

0.33

(_

0.32

 skall

0.31

 objectAtIndex

0.29

(!_

0.26

 getNumber

0.26

:-)

0.26

例文帳に追加

0.26

 "'";

0.26

,—

0.26

Activations Density 1.758%

references to historical conflicts and treaties involving national powers

No Comments

No Known Activations