INDEX

Explanations

quantifiable or measurable attributes within textual context

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

Follows mathematical symbols or abbreviations

np_acts-logits-general · gemini-2.0-flash

multi-lingual listings

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

Diwedd

-0.85

ValueGeneration

-0.79

 ProtoMessage

-0.77

 CURIAM

-0.77

awtextra

-0.76

новниш

-0.74

ViewImports

-0.74

fortawesome

-0.73

AnchorStyles

-0.72

twimg

-0.72

POSITIVE LOGITS

 sitä

0.54

 jure

0.51

 इसका

0.50

 ervan

0.50

 pojed

0.48

cale

0.46

وزی

0.43

 इसकी

0.42

::=

0.42

它的

0.42

Activations Density 0.936%

quantifiable or measurable attributes within textual context

Follows mathematical symbols or abbreviations

multi-lingual listings

No Comments

No Known Activations