INDEX

Explanations

key terms associated with data evaluation and analysis processes

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

determining criteria, charges, or winners

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 utafitiHapana

-0.63

 BorderSide

-0.61

WriteAttribute

-0.57

']],

-0.57

RectangleBorder

-0.56

copyWith

-0.53

requireNonNull

-0.52

addPreferredGap

-0.52

]")]

-0.52

tonode

-0.52

POSITIVE LOGITS

medim

0.43

tagHelperRunner

0.39

oredCriteria

0.37

 came

0.36

 rescate

0.36

was

0.35

 للمعارف

0.33

 went

0.33

를

0.31

 насељу

0.31

Activations Density 0.204%

key terms associated with data evaluation and analysis processes

determining criteria, charges, or winners

No Comments

No Known Activations