INDEX

Explanations

references to technical specifications and processes involving materials or applications in a structured context

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

"tr" or "tra" (case-insensitive)

np_acts-logits-general · gemini-2.0-flash

trapped, traced, trakt, tray, tr

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 nahilalakip

-0.87

دانشنامهٔ

-0.72

SourceChecksum

-0.61

 doInBackground

-0.60

-------------</

-0.59

enschappelijke

-0.58

basicConfig

-0.57

kloped

-0.56

 Voigt

-0.56

 Leno

-0.56

POSITIVE LOGITS

Tra

2.12

tra

2.02

Tra

1.96

tra

1.92

TRA

1.86

Tr

1.85

TR

1.84

Tr

1.75

 Тра

1.70

TR

1.68

Activations Density 0.455%

references to technical specifications and processes involving materials or applications in a structured context

"tr" or "tra" (case-insensitive)

trapped, traced, trakt, tray, tr

No Comments

No Known Activations