INDEX

Explanations

structured data formats and terms related to definitions or specifications in documentation

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

Mathematical or programming-related expressions

np_acts-logits-general · gemini-2.0-flash

zero quadratic form

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

ⓧ

-0.58

principalColumn

-0.57

RectangleBorder

-0.55

 kasarigan

-0.55

extAlignment

-0.53

Spolja

-0.51

+#+#

-0.51

 esternos

-0.51

tvguidetime

-0.50

yntaxException

-0.50

POSITIVE LOGITS

 Wild

0.38

 estan

0.32

TypedDataSet

0.32

اكل

0.32

Wild

0.31

 wild

0.31

 ihop

0.31

 asti

0.31

 Sher

0.31

per

0.30

Activations Density 1.931%

structured data formats and terms related to definitions or specifications in documentation

Mathematical or programming-related expressions

zero quadratic form

No Comments

No Known Activations