INDEX

Explanations

numeric values, specifically those related to measurements or data points

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

usercontent

-0.70

プーン

-0.65

wapV

-0.64

leč

-0.64

 Cheung

-0.62

 FormGroup

-0.62

<em>

-0.62

Pp

-0.62

────────

-0.61

Tear

-0.60

POSITIVE LOGITS



0.94

Datuak

0.85

)");

0.83

/>";

0.83

|<\

0.80

……"

0.80

 dieß

0.79

 Dage

0.78

 IMDG

0.78

jooq

0.78

Activations Density 0.587%

numeric values, specifically those related to measurements or data points

No Comments

No Known Activations