INDEX

Explanations

sections related to computational tasks and programming logic

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

Powers of two

np_acts-logits-general · gemini-2.0-flash

numbers and code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

ValueStyle

-0.58

toor

-0.57

abestanden

-0.53

Behavior

-0.53

 behaviors

-0.50

behavior

-0.50

 behaviours

-0.49

 Liberties

-0.49

Revenir

-0.49

 fizer

-0.49

POSITIVE LOGITS

AddTagHelper

0.59

 Falling

0.53

<<(

0.52

tehen

0.51

WebMethod

0.50

 AssemblyCompany

0.49

 raided

0.49

Falling

0.48

EnableWeb

0.47

libft

0.47

Activations Density 0.448%

sections related to computational tasks and programming logic

Powers of two

numbers and code

No Comments

No Known Activations