INDEX

Explanations

points in numerical or coded formats followed by contextual information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

GOTREF

-0.65

 MainAxisSize

-0.55

testens

-0.54

legged

-0.53

 lenker

-0.51

 betweenstory

-0.51

})).

-0.50

')));

-0.48

مصادر

-0.47

ismet

-0.47

POSITIVE LOGITS

MessageOf

0.87

MOQ

0.86

 exportation

0.86

 exporter

0.82

 wholesale

0.79

 exporting

0.77

+#+#

0.77

 exporters

0.75

 export

0.75

 Export

0.73

Activations Density 0.073%

points in numerical or coded formats followed by contextual information

No Comments

No Known Activations