INDEX

Explanations

terms related to media and broadcasting, particularly in reference to programs and sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Phillips

-0.58

 rails

-0.56

 Wolfs

-0.53

 Serves

-0.51

hls

-0.50

ίας

-0.49

Serves

-0.49

EDS

-0.49

ps

-0.48

Watts

-0.48

POSITIVE LOGITS

queryInterface

0.92

tableFuture

0.86

tagext

0.82

verwijspagina

0.81

*/;

0.79

 nahilalakip

0.79

 bezeichneter

0.78

SharedDtor

0.77

 وتسجيلات

0.76

})*/

0.75

Activations Density 0.907%

terms related to media and broadcasting, particularly in reference to programs and sources

No Comments

No Known Activations