INDEX

Explanations

terms related to numerical analysis and computational methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 numerical

-1.29

 numerically

-1.17

 Numerical

-1.07

numerical

-1.00

 numeric

-0.98

Numerical

-0.98

 integer

-0.88

integer

-0.76

Enum

-0.73

numeric

-0.73

POSITIVE LOGITS

 désolés

0.66

tableFuture

0.58

-};

0.58

//};

0.55

0.54

};*/

0.53

tinya

0.53

atán

0.52

GEBURTS

0.52

uchos

0.52

Activations Density 0.378%

terms related to numerical analysis and computational methods

No Comments

No Known Activations