INDEX

Explanations

keywords and identifiers related to programming and software structure

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

code constructs and identifiers

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

-0.37

MENAFN

-0.31

깥

-0.29

心想

-0.28

 hẹn

-0.28

The

-0.28

 terms

-0.27

 anti

-0.27

Che

-0.26

POSITIVE LOGITS

 indígen

0.67

 Geſch

0.66

.*")]

0.64

 tartalomajánló

0.63

 laſſen

0.63

 increí

0.62

 müſſen

0.61

 للاسماء

0.61

 ſeinen

0.58

 beſch

0.58

Activations Density 0.023%

keywords and identifiers related to programming and software structure

code constructs and identifiers

No Comments

No Known Activations