INDEX

Explanations

technical terms related to programming and software functionality

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

Tokens followed by function or setting names

np_acts-logits-general · gemini-2.0-flash

calendar settings

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

 isNameExpr

-0.74

^(@)

-0.74

 Мексичка

-0.73

vtk

-0.64

parsedMessage

-0.63

ksikon

-0.62

(\<

-0.60

OGND

-0.59

 الاطلاع

-0.59

.}~\

-0.58

POSITIVE LOGITS

 atve

0.57

ency

0.55

0.51

BindView

0.50

 تضيفلها

0.50

**

0.49

ⓘ

0.48

 иск

0.48

Activations Density 0.205%

technical terms related to programming and software functionality

Tokens followed by function or setting names

calendar settings

No Comments

No Known Activations