INDEX

Explanations

references to upper and lower values or limits

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Grüße

-0.39

resultCode

-0.37

lalu

-0.35

 surely

-0.34

 LABOR

-0.34

 RoutedEventArgs

-0.33

Neste

-0.32

layoutControl

-0.32

ロボ

-0.32

google

-0.32

POSITIVE LOGITS

 Upper

0.94

Upper

0.89

commons

0.81

 upper

0.73

 UPPER

0.73

UPPER

0.73

upper

0.71

 Lower

0.70

 told

0.66

 Commons

0.65

Activations Density 0.089%

references to upper and lower values or limits

No Comments

No Known Activations