INDEX

Explanations

information about recent announcements and events related to companies and individuals

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

comedy competition series

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

Autoritní

-0.52

SourceChecksum

-0.47

 חיצוניים

-0.45

 estekak

-0.44

Rujuakan

-0.42

Begriffsklä

-0.41

 initComponents

-0.40

Abit

-0.39

TokenNameRPAREN

-0.38

 dulu

-0.37

POSITIVE LOGITS

 AssemblyProduct

0.50

LookAnd

0.42

 faſt

0.42

ſelf

0.41

AutoField

0.40

quirrel

0.40

ſelves

0.39

 onData

0.39

SerializedSize

0.38

 otomatig

0.38

Activations Density 0.008%

information about recent announcements and events related to companies and individuals

comedy competition series

No Comments

No Known Activations