INDEX

Explanations

phrases that provide information about individuals, particularly those related to their achievements or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits



-0.75

PreferredItem

-0.60

 flesta

-0.57

 utanför

-0.57

ByDefault

-0.56

manera

-0.55

 للاسماء

-0.54

 varandra

-0.53

ImageContext

-0.53

 humains

-0.52

POSITIVE LOGITS

});*/

0.67

 useRef

0.62

gdx

0.61

arraycopy

0.60

*/;

0.59

 previously

0.59

MemoryWarning

0.58

 onAnimation

0.58

Nar

0.58

databind

0.57

Activations Density 0.290%

phrases that provide information about individuals, particularly those related to their achievements or actions

No Comments

No Known Activations