INDEX

Explanations

references to modules in programming documentation

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

Code or text referencing "module"

np_acts-logits-general · gemini-2.0-flash

module or NgModule

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 species

-0.61

 Frisch

-0.58

 Belo

-0.56

 Raub

-0.55

species

-0.55

Xr

-0.54

 Minas

-0.53

 Species

-0.51

Mâ

-0.51

 Agatha

-0.50

POSITIVE LOGITS

 Modules

1.33

 modules

1.31

NgModule

1.27

 NgModule

1.20

Modules

1.18

 Modul

1.17

 Module

1.16

MODULE

1.15

modules

1.14

 MODULE

1.13

Activations Density 0.231%

references to modules in programming documentation

Code or text referencing "module"

module or NgModule

No Comments

No Known Activations