INDEX

Explanations

code related to the NumPy library operations and functions

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

"np" and related numpy code

np_acts-logits-general · gemini-2.0-flash

numpy library usage

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FilterChain

-0.57

ğından

-0.57

TestingModule

-0.56

findOrFail

-0.55

uncias

-0.55

\|^{

-0.55

uspiel

-0.54

'],$

-0.54

...

-0.54

^(

-0.54

POSITIVE LOGITS

np

0.93

 numpy

0.77

np

0.75

 ModelExpression

0.69

XtraEditors

0.69

 BoxDecoration

0.67

glm

0.66

umpy

0.66

 Catholicism

0.65

UnknownFieldSet

0.65

Activations Density 0.036%

code related to the NumPy library operations and functions

"np" and related numpy code

numpy library usage

No Comments

No Known Activations