INDEX

Explanations

references to specific brands or product names

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

которые

-0.97

etheless

-0.95

webElementXpaths

-0.94

 resourceCulture

-0.88

GEBURTSDATUM

-0.85

нрави

-0.81

клопе

-0.79

rrggbb

-0.76

imantan

-0.73

queryInterface

-0.70

POSITIVE LOGITS

Com

0.54

Co

0.54

Ra

0.53

Tra

0.51

Am

0.51

Ma

0.51

Con

0.49

Rec

0.47

Par

0.47

Jo

0.46

Activations Density 0.700%

references to specific brands or product names

No Comments

No Known Activations