INDEX

Explanations

references to algorithms

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

identifying an algorithm

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

thenReturn

-0.47

})`

-0.44

'):

-0.40

Нет

-0.40

 West

-0.40

'}>

-0.40

Dread

-0.40

 mere

-0.40

*)&

-0.40

 нет

-0.39

POSITIVE LOGITS

 algorithm

1.82

 algorithms

1.70

 Algorithm

1.66

 Algorithms

1.65

Algorithm

1.54

algorithm

1.52

 algoritmo

1.52

 algorit

1.51

Algorithms

1.48

算法

1.32

Activations Density 0.011%

references to algorithms

identifying an algorithm

No Comments

No Known Activations