INDEX

Explanations

mathematical notation related to transformations and equivalences in advanced theoretical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 للاسماء

-0.91

 صوتيه

-0.89

findpost

-0.81

 cherchés

-0.80

 }}$}

-0.76

 myſelf

-0.75

 ComVisible

-0.74

contentLoaded

-0.73

 للمعارف

-0.71

 Administrativna

-0.70

POSITIVE LOGITS

''

0.94

''

0.80

‘‘

0.77

’’

0.77

”

0.73

”

0.73

``

0.72

“

0.72

"""

0.67

Activations Density 0.307%

mathematical notation related to transformations and equivalences in advanced theoretical contexts

No Comments

No Known Activations