INDEX

Explanations

structured data formats or tabular representations

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

LaTeX tabular environments

np_acts-logits-general · gemini-2.0-flash

tables with aligned columns

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

ffindor

-0.50

 Belast

-0.50

 quadros

-0.45

 участь

-0.44

 Belastung

-0.43

नलिखित

-0.42

 contribution

-0.42

 results

-0.42

 FBref

-0.41

 enfri

-0.41

POSITIVE LOGITS

|}

0.82

 ***!

0.80

 <<<<<<<<<<<<<<

0.75

 resourceCulture

0.71

Personensuche

0.68

httphttps

0.67

ьаж

0.65

||}

0.65

SequentialGroup

0.64

\{\\

0.63

Activations Density 0.072%

structured data formats or tabular representations

LaTeX tabular environments

tables with aligned columns

No Comments

No Known Activations