INDEX

Explanations

components related to lecture content and assignments

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

course lecture and discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

="@+

-0.36

 Мексичка

-0.35

 Италијани

-0.33

 Савезне

-0.29

Démographie

-0.28

wapV

-0.28

 alimenti

-0.27

 MenuView

-0.27

rawd

-0.27

intios

-0.27

POSITIVE LOGITS

RegistryLite

0.65

 lecture

0.58

 Lecture

0.57

 lectures

0.57

 Lectures

0.56

lecture

0.55

Lecture

0.54

 lecturing

0.51

 Lect

0.51

CppMethod

0.51

Activations Density 0.165%

components related to lecture content and assignments

course lecture and discussion

No Comments

No Known Activations