INDEX

Explanations

references to classification and categorization processes

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

Toponymie

-0.39

initComponents

-0.38

posedge

-0.36

 pres

-0.35

 Condiciones

-0.35

Біографія

-0.34

 חיצוניים

-0.34

úrese

-0.33

 bugged

-0.33

gelopen

-0.33

POSITIVE LOGITS

 category

1.06

 categories

0.97

 categorize

0.93

 categorization

0.91

 kategori

0.88

 Category

0.87

 classification

0.85

 Categories

0.85

 CATEGORY

0.85

categories

0.84

Activations Density 0.656%

references to classification and categorization processes

No Comments

No Known Activations