INDEX

Explanations

programming syntax constructs and operators

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

code and mathematical indexing

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

 meilleures

-0.53

 szerző

-0.49

 zagro

-0.46

 picioare

-0.46

таратура

-0.46

 laikā

-0.45

 vectorielle

-0.45

 meilleure

-0.45

 nôtre

-0.45

 experimentado

-0.44

POSITIVE LOGITS

Ie

0.59

iid

0.56

0.54

Ii

0.53

iI

0.53

IJ

0.51

iis

0.50

iiii

0.50

iin

0.50

Ii

0.48

Activations Density 0.128%

programming syntax constructs and operators

code and mathematical indexing

No Comments

No Known Activations