INDEX

Explanations

actions and phrases related to fighting and overcoming struggles

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

conflict, struggle, or disagreement

np_acts-logits-general · gemini-2.0-flash

fight and battle

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 kasarigan

-0.75

]")]

-0.68

 AssemblyCulture

-0.61

 kaarangay

-0.60

GEBURTSDATUM

-0.59

 ***!

-0.59

 виправивши

-0.57

----</

-0.55

rungsseite

-0.55

<pad>

-0.54

POSITIVE LOGITS

 fight

1.09

 Fight

1.07

fight

1.06

 fought

1.01

Fight

1.00

 FIGHT

1.00

 battle

0.98

 fighting

0.98

battle

0.95

 Battle

0.93

Activations Density 0.258%

actions and phrases related to fighting and overcoming struggles

conflict, struggle, or disagreement

fight and battle

No Comments

No Known Activations