INDEX

Explanations

programming-related concepts and terminology

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

Code snippets and error messages

np_acts-logits-general · gemini-2.0-flash

vpn Site, finds that

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Nowadays

-0.54

Nowadays

-0.50

 Moreover

-0.50

 convenable

-0.49

Moreover

-0.49

middlewares

-0.47

 nowadays

-0.47

 remarquable

-0.47

 transfert

-0.46

 devenu

-0.46

POSITIVE LOGITS

Datuak

0.76

 noDo

0.63

 &___

0.62

checkFor

0.56

]")]

0.56

ennifer

0.56

esque

0.54

eqn

0.54

 prepping

0.53

ɹ

0.53

Activations Density 1.001%

programming-related concepts and terminology

Code snippets and error messages

vpn Site, finds that

No Comments

No Known Activations