INDEX

Explanations

mathematical expressions involving quantifiers and set notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Aufbau

-0.44

tagHelperRunner

-0.43

 настро

-0.42

hezza

-0.41

Tabbed

-0.41

 Colonial

-0.41

🗳

-0.40

Spoljašnje

-0.40

otonic

-0.40

FlowLayout

-0.39

POSITIVE LOGITS

 '\\;'

0.71

GEBURTSDATUM

0.49

complexContent

0.48

íslu

0.46

 ब्रेकडाउन

0.46

UseVisualStyle

0.46

Personendaten

0.46

 Wiktionnaire

0.42

fjspx

0.42

♼

0.42

Activations Density 1.515%

mathematical expressions involving quantifiers and set notations

No Comments

No Known Activations