INDEX

Explanations

code syntax and punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

########.

-0.79

 للمعارف

-0.78

homonymie

-0.65

findpost

-0.65

 beginnetje

-0.65

RTEX

-0.63

verwijspagina

-0.62

StandardCharsets

-0.62

 Roskov

-0.61

曖昧さ回避

-0.60

POSITIVE LOGITS

 circonst

0.63

}?>

0.55

antaranya

0.53

())));

0.53

harapkan

0.52

wakili

0.52

]]);

0.52

ebilir

0.52

importanza

0.51

 Juifs

0.50

Activations Density 0.177%

code syntax and punctuation

No Comments

No Known Activations