INDEX

Explanations

software-related licensing terms and conditions

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

Start of code block/header

np_acts-logits-general · gemini-2.0-flash

code headers and imports

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

PositiveButton

-0.57

Бахар

-0.56

 camp

-0.54

الدراسه

-0.53

ImageContext

-0.51

úgó

-0.51

kaper

-0.49

олові

-0.49

rensa

-0.48

makeConstraints

-0.48

POSITIVE LOGITS

RegressionTest

0.76

principalTable

0.63

 proximate

0.60

 Monark

0.58

จบ

0.55

 légale

0.55

 Bourgoin

0.53

RTGC

0.53

olverine

0.52

Activations Density 0.196%

software-related licensing terms and conditions

Start of code block/header

code headers and imports

No Comments

No Known Activations