INDEX

Explanations

code-related syntax, particularly related to importing libraries and declaring data types or modules

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

Code-related punctuation and symbols

np_acts-logits-general · gemini-2.0-flash

repeated and const declarations

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.71

GEBURTS

-0.70

 Савезне

-0.70

 ویکی‌پدی

-0.69

хьтан

-0.68

 indígen

-0.66

 Biôgrafia

-0.66



-0.65

titleMargin

-0.61

rungsseite

-0.60

POSITIVE LOGITS

 ditto

0.35

 Occidente

0.32

jahres

0.31

 temu

0.30

 corresponding

0.30

本文

0.30

этому

0.30

 Similarly

0.30

 Likewise

0.29

하며

0.27

Activations Density 1.165%

code-related syntax, particularly related to importing libraries and declaring data types or modules

Code-related punctuation and symbols

repeated and const declarations

No Comments

No Known Activations