INDEX

Explanations

terms related to filtering and sorting actions

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

 وتسجيلات

-0.58

tagHelperRunner

-0.56

 muualla

-0.52

Predicted

-0.50

]}>

-0.50

Portály

-0.49

HasColumnName

-0.49

UseVisualStyle

-0.49

 Installing

-0.47

Installing

-0.46

POSITIVE LOGITS

IsMutable

0.61

LookAnd

0.57

 filter

0.55

Хьажоргаш

0.53

ρεσ

0.52

 search

0.52

 selection

0.51

 Selections

0.51

Espèce

0.50

clerview

0.50

Activations Density 0.397%

terms related to filtering and sorting actions

No Comments

No Known Activations