INDEX

Explanations

mathematical symbols and expressions related to probabilities and limits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 ویکی‌پدی

-0.77

 propOrder

-0.76

ReusableCell

-0.70

ThroughAttribute

-0.70

 oprot

-0.63

 ujednoznacz

-0.63

دانشنامهٔ

-0.63

 للاسماء

-0.62

 ſind

-0.61

AsUp

-0.57

POSITIVE LOGITS

left

1.09

 left

0.97

 Left

0.68

mfenced

0.65

 izquierda

0.64

 dejado

0.63

 lasciato

0.61

 LEFT

0.61

 leaving

0.60

Left

0.57

Activations Density 0.403%

mathematical symbols and expressions related to probabilities and limits

No Comments

No Known Activations

mathematical symbols and expressions related to probabilities and limits

No Comments

No Known Activations