INDEX

Explanations

instances of the word "simple" and its derivatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 للمعارف

-1.02

})*/

-0.86

 تانيه

-0.84

AndEndTag

-0.84

});*/

-0.79

endregion

-0.79

 consultato

-0.75

 AssemblyCompany

-0.74

 passim

-0.74

 DataLoader

-0.72

POSITIVE LOGITS

 simple

1.21

 Simple

1.18

Simple

1.17

 SIMPLE

1.07

simple

1.05

SIMPLE

1.02

 simpel

0.98

 straightforward

0.95

 simples

0.94

 简单

0.92

Activations Density 0.080%

instances of the word "simple" and its derivatives

No Comments

No Known Activations