INDEX

Explanations

specific terms and concepts related to legal, medical, and cultural contexts

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

Uncommon or misspelled words/tokens

np_acts-logits-general · gemini-2.0-flash

Mabon, Ala, xff, dB

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IBOutlet

-0.68

horabuena

-0.64

er

-0.59

Hiya

-0.56

 OkHttpClient

-0.54

expandindo

-0.53

 disambiguazione

-0.52

 transfieras

-0.51

 Neutr

-0.51

PvE

-0.50

POSITIVE LOGITS

й

0.51

akis

0.50

owsky

0.47

entibus

0.46

aky

0.45

webkit

0.44

vsky

0.44

qy

0.43

EndOf

0.43

 endIndex

0.42

Activations Density 3.253%

specific terms and concepts related to legal, medical, and cultural contexts

Uncommon or misspelled words/tokens

Mabon, Ala, xff, dB

No Comments

No Known Activations