INDEX

Explanations

references to technical standards and protocols, particularly those associated with IEEE

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

parsedMessage

-1.06

Kir

-0.80

Oc

-0.76

 Kamal

-0.76

HttpPut

-0.76

Sop

-0.75

 Shahid

-0.75

 anta

-0.73

 Rabin

-0.73

Zag

-0.73

POSITIVE LOGITS

={{

0.85

 Aristi

0.81

Annie

0.78

 Sina

0.76

 Herzen

0.76

Rwanda

0.74

Axes

0.74

MPa

0.73

 Tirol

0.73

 IndexPath

0.72

Activations Density 1.432%

references to technical standards and protocols, particularly those associated with IEEE

No Comments

No Known Activations