INDEX

Explanations

references to numerical values, specifically related to counts or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 مُعرِّف

-0.61

subsubsection

-0.58

crip

-0.57

Ariel

-0.57

ScopeManager

-0.56

endmodule

-0.54

 transfieras

-0.54

<%=

-0.54

<i>

-0.50

nicze

-0.50

POSITIVE LOGITS

 Commandments

0.90

 invokingState

0.86

0.83

AndEndTag

0.83

 Downing

0.79

getKeyCode

0.76

 commandments

0.75

 kaynağından

0.74

তথ্যসূত্র

0.73

 Tors

0.71

Activations Density 0.339%

references to numerical values, specifically related to counts or measurements

No Comments

No Known Activations