INDEX

Explanations

complex data structures or formats, particularly in programming or technical contexts

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

Followed by curly braces

np_acts-logits-general · gemini-2.0-flash

JSON definitions and data entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

########.

-0.58

errHandler

-0.47

 administracy

-0.46

 sexuales

-0.45

 caras

-0.45

処

-0.43

 shown

-0.42

mû

-0.42

مل

-0.41

дей

-0.41

POSITIVE LOGITS

 pinulongan

0.82

 esternos

0.82

 initComponents

0.77

 متعلقه

0.75

Hentet

0.75

ReusableCell

0.74

الإنجليزية

0.73

awtextra

0.71

ValueStyle

0.70

 للمعارف

0.70

Activations Density 0.030%

complex data structures or formats, particularly in programming or technical contexts

Followed by curly braces

JSON definitions and data entities

No Comments

No Known Activations