INDEX

Explanations

phrases related to programming and software terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

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

 nakalista

-0.67

 eletr

-0.59

NameInMap

-0.58

"}"

-0.58

 eletrônico

-0.58

})));

-0.56

 dưới

-0.56

(");

-0.54

 دیکھیے

-0.53

POSITIVE LOGITS

 Valid

0.68

Valid

0.64

 valid

0.63

 henvisninger

0.62

LR

0.56

Explicación

0.54

первых

0.54

ContentAsync

0.53

amsmath

0.53

valid

0.53

Activations Density 2.413%

phrases related to programming and software terms

No Comments

No Known Activations