INDEX

Explanations

technical references and terms related to devices and databases

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

device, networks, binding site, vessel, code, population

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

曖昧さ回避

-0.49

脚注の使い方

-0.48

 itſelf

-0.47

endish

-0.45

 purpoſe

-0.43

 raiſ

-0.43

 themſelves

-0.42

AddHtmlAttribute

-0.41

 poffible

-0.41

 OMITBAD

-0.41

POSITIVE LOGITS

 دیکھیے

0.57

__(/*!

0.52

 Photocase

0.47

 Hake

0.45

الحياه

0.43

TryDecodeAsNil

0.40

 GenerationType

0.39

注意事

0.39

StoryboardSegue

0.39

 незавершена

0.38

Activations Density 0.223%

technical references and terms related to devices and databases

device, networks, binding site, vessel, code, population

No Comments

No Known Activations