INDEX

Explanations

environment variables and configurations in code

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

`getenv` or `Uri` prefixes

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

ListItemIcon

-0.46

 casting

-0.46

 createSprite

-0.46

GraphicsUnit

-0.46

 quadrat

-0.45

ECES

-0.44

栩

-0.44

TableAdapter

-0.44

 Helf

-0.44

toda

-0.43

POSITIVE LOGITS

ThroughAttribute

0.44

URLException

0.42

contentLoaded

0.41

CheckBreak

0.40

 سكانية

0.39

 SafeMath

0.37

colgroup

0.37

PostInfinity

0.36

StateException

0.36

 gebeurt

0.33

Activations Density 0.007%

environment variables and configurations in code

`getenv` or `Uri` prefixes

No Comments

No Known Activations