INDEX

Explanations

terms related to scientific experiments and measurements

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

Part of a scientific apparatus/experiment

np_acts-logits-general · gemini-2.0-flash

technical term plus descriptor

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personendaten

-0.99

AndEndTag

-0.98

rungsseite

-0.87

 للاسماء

-0.86

 ExecuteAsync

-0.85

webElementXpaths

-0.82

 myſelf

-0.82

 Theſe

-0.82

 &___

-0.82

 مشين

-0.80

POSITIVE LOGITS

0.64

 program

0.63

 just

0.62

...

0.58

 model

0.57

de

0.56

and

0.55

dit

0.55

<eos>

0.55

0.53

Activations Density 0.715%

terms related to scientific experiments and measurements

Part of a scientific apparatus/experiment

technical term plus descriptor

No Comments

No Known Activations