INDEX

Explanations

numerical quantifiers and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ViewFeatures

-0.60

-0.50

FXML

-0.44

 AssemblyCulture

-0.44

-0.43

 îles

-0.42

 ahol

-0.42

 lendemain

-0.38

 ilha

-0.38

POSITIVE LOGITS

Personendaten

0.84

 Normdatei

0.83

ruff

0.80

SharedDtor

0.80

GeneratedMessage

0.80

Obrázky

0.80

DllImport

0.78

Šaltiniai

0.77

 Baillargeon

0.75

 تانيه

0.75

Activations Density 0.713%

numerical quantifiers and comparisons

No Comments

No Known Activations