INDEX

Explanations

rotational and transformation-related terms in graphical or mathematical 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

=$?

-0.57

setVerticalGroup

-0.49

}');

-0.48

tegen

-0.48

 INSEE

-0.47

 Carton

-0.47

enderror

-0.45

 treffen

-0.45

 marlin

-0.45

сно

-0.45

POSITIVE LOGITS

 resourceCulture

0.85

Tembelea

0.69

UnsafeEnabled

0.64

kloped

0.63

withIdentifier

0.61

íncia

0.58

ябре

0.57

хьтан

0.56

 يتيمه

0.56

openSession

0.56

Activations Density 1.339%

rotational and transformation-related terms in graphical or mathematical contexts

No Comments

No Known Activations