INDEX

Explanations

references to the concept of "Ne," especially in various contexts and usages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ellschaft

-0.56

 تانيه

-0.55

 createSprite

-0.55

CodeAttribute

-0.54

ccoli

-0.54

⁠

-0.53

TargetException

-0.53

ọa

-0.53

ArrowToggle

-0.53

})*/

-0.52

POSITIVE LOGITS

Ne

0.71

Ne

0.65

 Neff

0.65

 /\.(

0.59

 Neves

0.56

 Nebu

0.54

 Neel

0.54

Filmografie

0.54

 Neumann

0.53

 cherchés

0.53

Activations Density 0.127%

references to the concept of "Ne," especially in various contexts and usages

No Comments

No Known Activations