INDEX

Explanations

references to recommendations or guidelines

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Hauptartikel

-0.94

VIAF

-0.75

 VIAF

-0.72

Klu

-0.70

flik

-0.67

 Audiodateien

-0.67

Nix

-0.66

hline

-0.64

air

-0.64

 face

-0.64

POSITIVE LOGITS

 recommends

1.49

 recommended

1.41

 recommend

1.40

 Recommend

1.37

Recommendations

1.35

 Recommendations

1.35

 recommendations

1.34

 Recommendation

1.32

 RECOMMENDED

1.28

 Recomend

1.28

Activations Density 0.073%

references to recommendations or guidelines

No Comments

No Known Activations