INDEX

Explanations

terms related to HTTP redirects and associated actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

##

-0.76

--

-0.67

++

-0.65

[]){

-0.64

insic

-0.64

})();

-0.62

__':

-0.60

__":

-0.58

KIT

-0.58

choly

-0.58

POSITIVE LOGITS

 redirect

0.69

country

0.69

redirect

0.64

 الرياضيه

0.64

 redirected

0.61

 redirects

0.61

 Country

0.60

Country

0.59

mp

0.58

 Redirect

0.57

Activations Density 0.084%

terms related to HTTP redirects and associated actions

No Comments

No Known Activations