INDEX

Explanations

occurrences of the numpy library and its functions

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

Mentions or uses "np" to refer to numpy

np_acts-logits-general · gemini-2.0-flash

numpy array or NP IV

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

multirow

-0.61

tetés

-0.57

endpush

-0.57

DeleteBehavior

-0.56

لاعب

-0.56

AutoScaleMode

-0.55

Хьажоргаш

-0.55

!$

-0.54

HandlerContext

-0.54

CloseOperation

-0.53

POSITIVE LOGITS

 snippetHide

0.66

expandindo

0.62

 <<<<<<<<<<<<<<

0.57

#+#

0.55

 BoxDecoration

0.53

 autorytatywna

0.53

aarrggbb

0.52

 startY

0.51

atifs

0.51

glm

0.51

Activations Density 0.033%

occurrences of the numpy library and its functions

Mentions or uses "np" to refer to numpy

numpy array or NP IV

No Comments

No Known Activations