INDEX

Explanations

references to the degree and extent of various phenomena or concepts, particularly in scientific or analytical contexts

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

nextPage

-0.59

ContentAsync

-0.57

createNewFile

-0.51

pushFollow

-0.50

 başka

-0.50

からない

-0.50

ytte

-0.50

uxxxx

-0.49

gar

-0.48

|()

-0.48

POSITIVE LOGITS

 extent

1.33

 Extent

1.15

extent

1.14

 degree

0.99

 level

0.95

 степень

0.89

程度

0.88

Extent

0.87

 насколько

0.85

 Degree

0.84

Activations Density 0.349%

references to the degree and extent of various phenomena or concepts, particularly in scientific or analytical contexts

No Comments

No Known Activations