INDEX

Explanations

elements related to coding or programming concepts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

mathematical 'l' terms

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

Negative Logits

лтамалар

-0.50

envolvimento

-0.50

RegressionTest

-0.49

 investissements

-0.49

 económicas

-0.46

 écrans

-0.46

 apsau

-0.46

 investissement

-0.45

 muestras

-0.45

toHave

-0.45

POSITIVE LOGITS

ChildScrollView

0.53

lllll

0.51

LL

0.50

llll

0.49

Ll

0.49

lll

0.46

<thead>

0.45

LL

0.45

 فريبيس

0.45

ll

0.44

Activations Density 0.001%

elements related to coding or programming concepts

mathematical 'l' terms

No Known Activations