INDEX

Explanations

patterns in numerical data and structured elements within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

forChild

-0.62

 pacchetto

-0.51

 crystall

-0.50

yszer

-0.50

 incontra

-0.50

Fprintf

-0.50

 Celui

-0.48

 prés

-0.46

 indoss

-0.46

 voort

-0.46

POSITIVE LOGITS

,:),

0.88

webElementXpaths

0.87

/}.

0.85

*/].

0.83

)$/,

0.83

cleos

0.81

帖最后由

0.80

}`).

0.79

__]

0.79

//

0.78

Activations Density 0.200%

patterns in numerical data and structured elements within the text

No Comments

No Known Activations