INDEX

Explanations

elements related to programming code and documentation

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

license information and code comments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 author

-1.39

 authors

-1.38

author

-1.24

 Authors

-1.23

 authored

-1.21

authors

-1.20

Authors

-1.16

 Author

-1.16

 AUTHOR

-1.14

Author

-1.13

POSITIVE LOGITS

IActionResult

0.42

 محفوظة

0.39

email

0.36

 initComponents

0.36

 modification

0.35

 purpose

0.35

 modifications

0.34

purpose

0.34

 email

0.33

ANTLR

0.33

Activations Density 0.021%

elements related to programming code and documentation

license information and code comments

No Comments

No Known Activations