INDEX

Explanations

elements or markers in structured data or lists

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

Mathematical or technical notation

np_acts-logits-general · gemini-2.0-flash

three years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

 للاسماء

-0.51

 disambiguazione

-0.51

stylers

-0.44

 kohdetta

-0.43

nestjs

-0.42

Portail

-0.41

 htmlFor

-0.41

Rujuakan

-0.41

 utafitiHapana

-0.40

ContentAsync

-0.38

POSITIVE LOGITS

IUrlHelper

0.48

 Anchor

0.48

FormTagHelper

0.46

 Retrospective

0.45

\{\\

0.44

 Anch

0.44

Perman

0.43

Transient

0.43

 Knot

0.43

SOUNDBITE

0.42

Activations Density 0.890%

elements or markers in structured data or lists

Mathematical or technical notation

three years

No Comments

No Known Activations