INDEX

Explanations

instances of data packet processing and routing terminology

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

destination or directed messages

np_acts-logits-general · gemini-2.0-flash

destination and recipient

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

RegressionTest

-0.53

COUVER

-0.52

SequentialGroup

-0.49

்கு

-0.44

ysuckle

-0.43

centralwidget

-0.43

抽出

-0.42

抽

-0.42

ggia

-0.41

TypedDataSet

-0.41

POSITIVE LOGITS

 destinations

0.56

 destination

0.50

 destino

0.47

 destined

0.43

 Destinations

0.42

Destination

0.41

 destin

0.41

目的地

0.41

ViewFeatures

0.40

Intended

0.40

Activations Density 0.350%

instances of data packet processing and routing terminology

destination or directed messages

destination and recipient

No Comments

No Known Activations