INDEX

Explanations

features and attributes related to technological updates and implementations

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

"new" or its foreign equivalents

np_acts-logits-general · gemini-2.0-flash

new

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 szóci

-0.45

MethodManager

-0.44

ncbi

-0.43

州市

-0.42

 getBase

-0.41

RUnlock

-0.40

 getCode

-0.40

DataSnapshot

-0.40

टी

-0.40

ürtel

-0.39

POSITIVE LOGITS

new

3.90

new

3.31

 nuevos

2.91

 nieuwe

2.87

 nueva

2.86

 nuevas

2.83

 nuevo

2.80

新的

2.74

 neue

2.71

 neuen

2.70

Activations Density 1.057%

features and attributes related to technological updates and implementations

"new" or its foreign equivalents

new

No Comments

No Known Activations