INDEX

Explanations

information related to software updates and version changes

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

software updates

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

 soggetto

-0.43

eseorang

-0.42

 <>",

-0.41

 kysy

-0.39

ApiProperty

-0.38

extAlignment

-0.38

 henkilö

-0.37

 paroisse

-0.36

AnchorTagHelper

-0.35

Traducción

-0.35

POSITIVE LOGITS

 updates

0.72

 Updates

0.61

 upgrades

0.60

 update

0.60

 firmware

0.57

MemoryWarning

0.56

updates

0.56

 changes

0.55

 upgrade

0.55

FunctionFlags

0.54

Activations Density 0.009%

information related to software updates and version changes

software updates

No Comments

No Known Activations