INDEX

Explanations

references to specific biological or chemical terms and entities

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

Applied Biosystems products

np_acts-logits-general · gemini-2.0-flash

Applied Biosystems

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

Bibliograf

-0.50

 Савезне

-0.46

 autorytatywna

-0.45

utilisons

-0.43

Билгалдахарш

-0.43

ChrTalk

-0.36



-0.31

лтемелер

-0.31

 Internasional

-0.31

GEBURTSDATUM

-0.31

POSITIVE LOGITS

<bos>

0.67

RTSC

0.54

0.53

 つ折り

0.51

 detail

0.51

0.50

 Manner

0.50

 CURLOPT

0.50

 secrets

0.50

 secret

0.49

Activations Density 0.798%

references to specific biological or chemical terms and entities

Applied Biosystems products

Applied Biosystems

No Comments

No Known Activations