INDEX

Explanations

reference markers or indicators in the text

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

after specific tokens (, Q, Field)

np_acts-logits-general · gemini-2.0-flash

no regrets or worst outcomes

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

RegistryLite

-0.86

addPreferredGap

-0.76

CppMethod

-0.71

++]=

-0.67

OGND

-0.66

Efq

-0.64

 gradova

-0.63

AutoField

-0.62

CreateModel

-0.62

]='\

-0.62

POSITIVE LOGITS

nor

1.33

 anymore

0.98

 tampoco

0.93

 either

0.80

nor

0.78

 nici

0.78

 sondern

0.76

any

0.76

Nor

0.75

 nicio

0.73

Activations Density 0.336%

reference markers or indicators in the text

after specific tokens (, Q, Field)

no regrets or worst outcomes

No Comments

No Known Activations