INDEX

Explanations

HTML and API-related code snippets, particularly those involving definitions and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 referrerpolicy

-0.76

 للمعارف

-0.72

发表于

-0.57

oolean

-0.56

RenderAtEndOf

-0.55

transQ

-0.54

лтемелер

-0.54

 onPostExecute

-0.52

SerializeField

-0.52

 afect

-0.51

POSITIVE LOGITS

 urmă

0.61

zzá

0.53

 démocratique

0.52

endregion

0.51

 duquel

0.50

 rarement

0.50

ImageContext

0.50

 Roskov

0.47

 uovo

0.47

 ویکی‌پدیا

0.47

Activations Density 0.170%

HTML and API-related code snippets, particularly those involving definitions and structures

No Comments

No Known Activations