INDEX

Explanations

discussion on grammatical structures and their classifications

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

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

awtextra

-0.54

islation

-0.52

 alpina

-0.49

]")]

-0.47

 feder

-0.46

 cordi

-0.46

MLLoader

-0.46

 Florence

-0.46

 spectre

-0.46

الحياه

-0.45

POSITIVE LOGITS

 nakalista

0.50

 souvent

0.44

afficheront

0.42

mobileqq

0.40

 felicità

0.40

 estructuras

0.40

 Exactos

0.40

 ""],

0.40

Autoritní

0.40

WebElementEntity

0.39

Activations Density 0.412%

discussion on grammatical structures and their classifications

No Comments

No Known Activations