INDEX

Explanations

syntax elements and control structures in code

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

code delimiters and email subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 ModelExpression

-0.68

évaluateur

-0.63

 nakalista

-0.59

Personendaten

-0.58

 للمعارف

-0.58

########.

-0.57

⟬

-0.57

Ⴈ

-0.56

তথ্য

-0.56

出版年

-0.56

POSITIVE LOGITS

reportWebVitals

0.40

/**

0.36

endpush

0.33

تقاوى

0.31

打

0.31

 الجز

0.30

//

0.29

 meub

0.29

用

0.29

Activations Density 0.011%

syntax elements and control structures in code

code delimiters and email subject

No Comments

No Known Activations