INDEX

Explanations

references to data representation and labeling in scientific contexts

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

or letters and their representation/association

np_acts-logits-general · gemini-2.0-flash

letter indicators and their designations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ItemLayout

-0.63

 VIAF

-0.57

PRWEB

-0.55

DeleteBehavior

-0.54

>{@

-0.53

 متعلقه

-0.52

ंदीखरीदारी

-0.51

ArrowToggle

-0.50

例文帳に追加

-0.49

 cherchés

-0.49

POSITIVE LOGITS

 letter

1.64

 letters

1.64

letter

1.45

letters

1.35

 Letter

1.33

 Letters

1.32

Letter

1.32

 lettre

1.30

 LETTER

1.27

 Buchstaben

1.25

Activations Density 0.419%

references to data representation and labeling in scientific contexts

or letters and their representation/association

letter indicators and their designations

No Comments

No Known Activations