INDEX

Explanations

numerical data related to health metrics

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

Numbers following a letter, often within brackets

np_acts-logits-general · gemini-2.0-flash

C followed by number

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 صوتيه

-0.63

CloseOperation

-0.62

ParallelGroup

-0.62

 Administrativna

-0.60

最快更新

-0.58

 مشين

-0.57

 թվական

-0.56

 snippetHide

-0.56

angelog

-0.55

farwyddwr

-0.54

POSITIVE LOGITS

fromnode

0.44

azgo

0.38

RTA

0.38

ulemon

0.38

########.

0.36

Firstly

0.35

 BaseActivity

0.35

zzleHttp

0.35

Carrière

0.35

/>";

0.35

Activations Density 1.604%

numerical data related to health metrics

Numbers following a letter, often within brackets

C followed by number

No Comments

No Known Activations