INDEX

Explanations

patterns and structures within numeric or formatted data

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

Numbers inside parentheses

np_acts-logits-general · gemini-2.0-flash

numbers and age ranges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 resourceCulture

-0.76

 kasarigan

-0.70

parsedMessage

-0.68

expandindo

-0.68

adaptiveStyles

-0.67

<unused74>

-0.67

 好文分享

-0.67

<unused16>

-0.67

[@BOS@]

-0.66

<unused41>

-0.66

POSITIVE LOGITS

GraphicsUnit

0.38

WillAppear

0.36

OrEqualTo

0.34

 Paglinawan

0.33

NameValuePair

0.33

‘

0.32

par

0.32

ve

0.32

borderFill

0.31

쳐

0.31

Activations Density 1.006%

patterns and structures within numeric or formatted data

Numbers inside parentheses

numbers and age ranges

No Comments

No Known Activations