INDEX

Explanations

references to legal and judicial terms or concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.95

 myſelf

-0.88

Efq

-0.88

)";

-0.86

Obrázky

-0.86

*/;

-0.84

")));

-0.84

InstanceState

-0.83

 itſelf

-0.83

 ModelExpression

-0.82

POSITIVE LOGITS

Sel

0.90

sel

0.90

Sel

0.78

eth

0.69

Cam

0.64

PF

0.61

 бу

0.60

pf

0.59

cel

0.59

cel

0.58

Activations Density 0.059%

references to legal and judicial terms or concepts

No Comments

No Known Activations